Beginner Guide · for Headhunters & Sales

Use Claude with confidence — in Sales and in Building.

No tech knowledge required. No generic AI phrases. This guide shows you visually, in the right order and with over 60 ready-to-use prompts, how to put Claude to work on real sales and building challenges from day one — from the danic.ai discovery call to the YouTube script.

60+
Example prompts to copy
10
Topic areas, step by step
Work & personal life kept separate
0
Prior knowledge required
LB
Lukas Bauer, 30
Headhunter · Sales · Content Creator · Berlin

"For 4 years I've been doing candidate search, plus dev and testing work. Now I'm starting in Sales at danic.ai, I want into the executive search game, and I'm producing precious metals content on the side. Three hats, one day — I need Claude as leverage, not as a toy."

Lukas accompanies you through every section of this guide. Every example comes from his real sales, recruiting, or content routine.

Learning Path

Three clear stages — no overwhelm

This is how you build confidence step by step, without wrestling with every feature at once on day 1.

Day 1 — First wins

Create an account, understand the chat window, complete three simple tasks (danic pitch, cold email, research). Pure experimentation.

Go to the starter chapter

Week 1 — Projects and routines

Set up dedicated "rooms" for Sales, executive search, and precious metals content (Projects). Store templates and your own writing style once — Claude remembers.

Discover Projects

Month 1 — Your own assistants

Write system prompts, shape your own "team members" — e.g. a danic pitch assistant, a cold-outreach copywriter, a precious metals content scout.

Build system prompts
Quick Wins

Be impressed in 5 minutes

Three prompts that show the difference immediately. Just copy, paste into Claude, read the answer.

1. Cold outreach to a CTO for danic.ai

Chat prompt · 30 seconds
Write a LinkedIn direct message (max. 90 words) to the CTO of a German mid-sized company (200–500 employees, engineering roughly 20–40 people, in-house product development). I work in Sales at danic.ai. We build orchestrated fleets of coding agents (DANIC OS) that deliver software in days instead of months and are handed over completely to the internal team at the end — no agency lock-in. Proof point: a LinkedIn lead funnel was 44× faster than an agency quote (92 person-days instead of 4,064 person-days) at 94% test coverage. Tone: respectful, technically serious, no sales babble. CTA: a 20-minute sparring session to see whether a concrete use case fits his stack. Deliver three variants: (a) direct, (b) provocative question, (c) peer referral.

2. A tough reply to a critical LinkedIn comment

Chat prompt · 45 seconds
A senior engineer left the following comment under my LinkedIn post about danic.ai: "Agentic coding is hype. In any serious codebase, these agents produce technical debt within two weeks that costs more than what they saved. I'll believe it when I see it." Draft three variants of a professional, matter-of-fact reply: 1. A short, de-escalating reply that takes the objection seriously (max. 4 sentences). 2. A more detailed reply with a concrete proof point (LinkedIn lead funnel: 92 person-days vs. 4,064 person-days, 94% coverage) — without lecturing the engineer. 3. A reply that openly invites the engineer to discuss the use case in a 20-minute sparring session. Tone: respectful, technically serious, no marketing phrases. Never condescending toward the commenter — he is a potential multiplier.

3. Plan a solo city trip — in one go

Chat prompt · 60 seconds
Plan a 3-day solo trip to Lisbon for me in mid-September. Budget: 700 euros excluding flights. I'm 30, traveling alone, won't rent a car, love good food (no tourist traps), open to nightlife but not primarily clubs — more like small bars with music. During the day I like 1–2 serious agenda items (architecture, a museum, a day trip to the coast). Create: - Three hotels or boutique apartments in the mid-price range, well connected, quiet location - A relaxed daily plan: at most one fixed activity per day, plenty of slack - A plan B for each activity in case of bad weather - A list of 6 restaurants/bars in different neighborhoods, with a brief reason for each - A recommendation for a day trip (Sintra, Cascais, or Setúbal — with a clear recommendation why) At the end, list three things I'm probably not thinking of (e.g. tipping culture in Portugal, public transit pass, credit card acceptance).
That is exactly the point.

You don't need to know how to prompt "correctly". You just need to say what you want, for whom, in what tone, at what length — and which details you typically overlook. Claude takes care of the rest.

Before you get started: one sentence on privacy.

Never enter real, identifiable client, candidate, or customer data into Claude. Not the full name, not the email address, not the phone number, not the current employer. That is non-negotiable — and it isn't necessary either. In every example, we show you how to describe cases so that Claude answers as helpfully as possible without you taking on compliance risks. → Complete rules & examples

Ready for the first step?

Start with the chapter "What is Claude, anyway?" — five minutes of reading, and you have the foundation.

Basics · 5 minutes

What is Claude — and what is it not?

A comparison that actually fits: Claude is like a highly competent, fast, very well-read assistant — one who, however, doesn't "practice" a profession and remembers nothing you told him yesterday (unless you tell him again).

LB
Lukas asks
Headhunter · Berlin

"'It's a language model' isn't enough for me. I want to know: What can I realistically expect, where are the real limits, and which terms do I need to know?"

The analogy that fits

Picture Claude as a young, very smart assistant in a library. Over the past few years, this person has read millions of texts — studies, books, journal articles, forums, how-to guides. He can summarize, draft, structure, compare, and translate at lightning speed.

But: this person has never worked in sales themselves, has never run a consultation, is not licensed to practice — and their library reflects a specific point in time. They never leave the library unless you send them out (that's "web search"). And at the end of the day, they forget the conversation once you leave the room — unless you've set up a permanent desk for them (that's "Projects" and "Memory").

What this means for your day-to-day

Claude is ideal for everything you read, review, and cross-check yourself against clinical experience. He is not ideal as the sole decision-making authority on professionally risky topics. You remain the physician — Claude is the fast, friendly staff member.

What Claude can do — and what it can't

Claude is very good at…

  • Drafting texts (client letter, email, blog article, patient information text)
  • Simplifying complex content — to any language level you want
  • Structuring (lists, comparison tables, SOAP notes, pros/cons)
  • Translating between languages — including technical texts (engineering, law, finance)
  • Summarizing long documents (guidelines, PDFs, studies)
  • Brainstorming and collecting differential-diagnosis ideas
  • Building code, tables, small web apps, and visualizations
  • Describing and interpreting images (e.g. a screenshot of a LinkedIn profile, a photo of a business card)

Claude is bad or dangerous at…

  • Making independent clinical decisions (never without your review)
  • "Current" information without an active web search
  • Guarantees — hallucinations do happen, always cross-check
  • Real client and candidate data — never enter it in identifiable form
  • Legally binding statements without legal / tax review
  • Image generation (Claude does not generate images, videos, or audio)
  • Making phone calls, booking appointments itself (except with Connectors)
  • Remembering old conversations unless you enable that

How does it work, big picture?

You enter a prompt — that's simply your question or task. Claude processes this text and responds. You can follow up, correct, dig deeper. That's called a conversation.

You type or speak

A question, a task, a piece of text — in plain German or English. Long inputs are fine. So are attachments (PDF, images, Word).

Claude reads and processes everything in context

The "context" is Claude's short-term memory within the current chat. Very large, but limited. As long as the conversation is running, Claude can draw on everything that came before.

Claude responds — and you iterate

The first answer is rarely perfect. Just say what you want changed: "Shorter." "At B1 level." "With three examples." "In a different tone." That's the lever.

Optional: add tools

Web search, file upload, connections to Google Drive, Calendar, Notion, and more (so-called "Connectors"). With these, Claude can also do things instead of just answering.

Mini glossary — the eight words that keep coming up

Prompt
Your input to Claude. A question, an instruction, an assignment. The more precise (role, tone, length, audience, format), the better the result.
Model (Sonnet, Opus, Haiku)
The "version" of Claude that responds. Opus is the strongest and slowest, Sonnet a good all-rounder, Haiku the fastest for light tasks. For everyday use, the default setting is enough — you don't have to actively choose.
Context window
The "short-term memory" within a chat. Very large — you can paste in an 80-page PDF and Claude understands it as a whole. But: switch chats, and that context is gone.
Hallucination
When Claude confidently makes something up — a study, a dosage, a date, a source. It happens less often than with earlier models, but it does happen. Consequence: Always cross-check facts that matter commercially or legally. Better too often than too rarely.
System Prompt
The "job description" you give Claude once — role, tone, rules, preferences. It applies in all subsequent chats of a Project. More on this.
Project
A dedicated "workspace" with its own system prompt and its own files. E.g. danic Sales Outreach or Precious Metals Content. More on this.
Artifact
A "real document" or a small application that Claude builds to the right of the chat: a Word letter, an Excel spreadsheet, an interactive checklist, a small visualization. More on this.
Connector / MCP
A connection from Claude to an external service (Google Drive, Gmail, Calendar, Notion, …). MCP is just the technical name for this standard. You enable it once in the settings — and Claude can then, for example, add an appointment to your calendar without you having to switch tools.

Which model should I choose?

For 95% of all tasks in the sales pipeline and in your private life, Claude's default setting is the right one. You don't need to change anything. If you want the details:

Sonnet

The fast all-rounder. Ideal for emails, patient information texts, research, brainstorming, daily planning. Default in Claude Pro.

Opus

The strongest model. Worth it for long, complex tasks — e.g. when you want to have a 60-page guideline summarized or to draft a complex cover letter.

Haiku

The fastest, lightest model. For very short, quick queries — such as "What's that medication called again, the one with active ingredient X?".

Plain recommendation

Just leave it on the default setting. Only switch when you notice that a task really needs long answers or particularly difficult reasoning — then use Opus.

Feature · 8 minutes

The chat — your constant sparring partner.

The chat window is the fastest way to get something done with Claude. You open a new tab, type your question, get an answer, and refine. Here you'll learn what separates a good prompt from a bad one — and collect ten templates to copy that fit straight into your daily work.

When is the chat the right tool?

The chat is right for…

  • One-off, quick requests
  • Quick research and "what-if" questions
  • Spontaneous client communication
  • Ad-hoc translations or explanations
  • Summaries of long texts
  • Brainstorming sales strategies and objection handling

For recurring tasks, better to…

  • Set up a Project (see chapter)
  • Define your own system prompt
  • Upload important files permanently
  • That way Claude doesn't need a fresh briefing every time

The anatomy of a good prompt

A good prompt implicitly answers five questions: who (role), what (task), for whom (audience), how (tone & format), and what to watch out for (constraints). You don't have to phrase it in this order — but the more of these your prompt contains, the better the answer.

Bad → better → very good: the same task at three levels

❌ Level 1 — too vague
Write something about danic.ai for CTOs.
✓ Level 2 — solid standard
Write a short LinkedIn post about danic.ai aimed at CTOs. Audience: CTOs at mid-sized companies with 50-200 engineers. Tone direct, no marketing speak. Length approx. 150 words.
★ Level 3 — very good
Role: You are an experienced B2B copywriter who writes for tech sales. Task: Write a LinkedIn post for my profile about danic.ai. Audience: CTOs and VPs of Engineering at companies with 50-200 engineers. They may already use GitHub Copilot and are skeptical of hype. Tone and style: Direct, slightly counterintuitive, data-driven. NO buzzwords ("disruptive", "transformative", "synergistic", "revolutionary"). The way Daniel Deckert or Pieter Levels would write. Format: - Hook in the first 2 lines (provocative or counterintuitive, but no clickbait) - Three short paragraphs, 2-3 sentences each - One concrete number from the danic.ai cases (e.g. 44× faster, 26× cheaper, 100+ agents in parallel) - Closing: an open question or a clear takeaway — NO "What do you think?" filler Constraints: - 800-1,200 characters - Maximum 3 hashtags at the end - NO emojis at the beginning - No sweeping statements about customers At the end, give me two alternative hooks to choose from.
The pattern to take away

Role · Task · Audience · Tone · Format · Constraints. If you keep these six building blocks in mind, you'll automatically write better prompts — no tricks and no prompt-engineering course required.

Ten ready-to-use prompts — straight from Lukas's daily work

You can copy each of these prompts as-is, adapt it to your situation, and paste it into Claude.

Sales Client Communication Beginner

1. Write a danic.ai explanation a CTO will understand

"In a LinkedIn message, I have 30 seconds to explain danic.ai. If I say 'agentic orchestration layer', the CTO is gone."

Prompt
Write three variants of how I can explain danic.ai in a first LinkedIn message to a CTO (mid-sized company, ~80 engineers, TypeScript+Python stack). Maximum 3 sentences per variant. Key facts: - danic.ai builds companies their own AI agent development team and hands it over completely - 100+ coding agents in parallel (reviewers, testers, architects) on the customer's stack - No tool sales, no lock-in, the setup runs on the customer's infrastructure (Claude API by default; optionally a self-hosted LLM) - Reference case: 44× faster, 26× cheaper than a standard agency Variants: A — Dry and technical (for old-school CTOs) B — Insight-first (for tech-savvy VPs, with one counterintuitive observation) C — Founder-to-founder (for solo CTOs, as equals, slightly ironic) Rules: no buzzwords ("disruptive", "transformative", "synergistic"), no question at the end, clear ask in the last sentence.
Sales Research Beginner

2. Get a quick overview of market data on CTO salaries

"Tomorrow morning a client will ask: 'What does the market pay for a CTO at a Series B FinTech?' I need solid numbers — not whatever I happen to think I know."

Prompt with web search enabled
Research current salary data (2025/2026) for the following position: Role: CTO Stage: Series B Industry: FinTech (regulated B2B sector) Location: Berlin (with remote option) Engineering team size: 30-80 people Deliver in max. 300 words: 1. **Base salary range** (median + 25th/75th percentile), sources: Levels.fyi, Honeypot, Robert Half, Glassdoor — each with a date 2. **Variable components** (bonus, ESOP/VSOP) — typical Series B ranges 3. **Sign-on bonus** range and when it's typical 4. **Comparison with Series A and Series C** — where does B sit on the spectrum? 5. **Three 2025/2026 trends** moving the salary band (e.g. AI coding adoption lowers headcount needs — does that push down senior comp?) Important: - Sources with link and date - If data is contradictory — say so clearly and give me the range - If something is older than 2024 — flag it - Don't sell marketing claims from recruiting platforms as facts
Sales Administration Beginner

3. An empathetic rejection to recruiting tool vendors

"Three more vendor pitches in my inbox: a new ATS, an AI sourcing tool, a market data subscription. I want to decline all three politely but clearly — with no back door."

Prompt
Draft three short email rejections to SaaS vendor sales reps who want a meeting about their recruiting tools. Tone: polite, firm, no pressure to justify. I don't explain anything at length, but I do offer that materials can be sent by email. Variant 1: Very short, 3 sentences. Variant 2: Medium, noting that my calendar is full until further notice. Variant 3: With the option that materials are welcome by email. No substantive judgment of the product. No promises for the future. Business courtesy without coming across as ingratiating.
Sales Strategy Intermediate

4. Strategically brainstorm a candidate long list

"First exec search mandate: CTO for a Series B FinTech. The long list needs 40 names. I know the market from sourcing, but 'Director of Engineering' is not 'board-ready CTO'."

Prompt
Help me structure the search strategy for a CTO long list. Mandate: Series B FinTech, BaFin-regulated, ~80 engineers, Berlin hub + partial remote Must-haves: 10+ years of engineering leadership, at least one 50→200 scale-up, regulatory experience with BaFin/MaRisk, hands-on at the architecture level Nice-to-haves: open-source reputation, international experience No-gos: pure consulting track without operational line experience Structure the search by likelihood into three buckets: 1. **Sitting CTOs at a similar stage** — where exactly do I look (which companies, which LinkedIn filters)? 2. **Top VPs of Engineering just before the C-level jump** — indicators: how do I recognize readiness for the jump? 3. **Comeback candidates** — ex-CTOs on sabbatical, in consulting, at small startups — where are they? Per bucket: 3 concrete filter combinations for LinkedIn Recruiter, plus 3 indicators for "genuinely movable" (tenure, recent posts, promotion standstill). At the end, flag the two "red flags" that make me screen someone out on second look (e.g. a history of too-short tenures, consultant-only language). Important: You are my sparring partner for the methodology, not my research operator. No real names — methodology only.
Personal Personal life Beginner

5. A speech for a good friend's 30th birthday

"My best friend is turning 30. He expects words, not silence. I can't find a way to start."

Prompt
I need a short, honest speech for a good friend's 30th birthday. A few notes about him: - His name is Tarek, born in 1996 - Software engineer, 6 years at the same company — unusually loyal - Plays chess semi-professionally, rides a motorcycle, cooks Lebanese food - We've known each other for 12 years — together through university, a failed startup, a move - Occasion: 25 guests, restaurant, casual setting — not too formal Write a speech of exactly 90 seconds (approx. 220 words). Tone: warm, slightly self-deprecating, with one small, honest anecdote (you can invent a plausible one that fits his character — I'll adjust it). Three sections: 1) greeting & why I'm the one speaking today, 2) one specific quality I appreciate about him, 3) toast. Avoid kitsch, pathos, and "banquet clichés". Authentic, not a "ceremonial address".
Personal Finance Beginner

6. Prepare an insurance comparison

"I have three private health insurance offers on my desk. I want to understand them before I talk to the broker."

Prompt
I have three private health insurance (PKV) offers to compare (PDFs attached). Create for me: 1. A compact comparison table with the most important coverage points: - Deductible - Hospital (single/double room, head physician treatment) - Outpatient (vision aids, alternative practitioners, preventive care) - Dental (preservation, replacement, orthodontic treatment) - Premium refund if no claims are made - Switching/cancellation terms 2. Three critical questions I should ask the broker to make the differences visible. 3. Three points I should pay special attention to (overlooked cost traps, switching risks, standard age-related premium loadings). Write in German, factually, without advertising language. No recommendation for or against any provider — I decide. At the end, add a short note, if relevant, on what only an insurance broker can answer with binding authority.
Personal Learning Beginner

7. Revive a language

"I learned Spanish at university. I want to reactivate it on the side, without an app — 10 minutes a day."

Prompt
You are my personal Spanish coach. My level: about B1, with clear gaps in the subjunctive (subjuntivo) and conditional forms. Today's session (10 minutes): 1. Greet me in Spanish in two sentences. 2. Ask me three short questions about my day — I'll answer in simple sentences. 3. Correct me kindly when I get something wrong. Don't just point out the mistake — briefly explain the rule. 4. At the end: three new vocabulary words that fit the conversation, in a small table (Spanish — German — example sentence). If I answer in German, that's fine. Then correct me kindly and ask the question again in Spanish. Be patient but consistent.
Sales HR Intermediate

8. A job ad for a junior researcher in your recruiting business

"I need a junior researcher (10h/week) for sourcing on my exec search mandates. Maybe my old job ad is the reason nobody is applying."

Prompt
I'm hiring for a junior research position (10h/week, remote, working student or freelance) for my solo setup as a headhunter in Berlin. Tasks: LinkedIn sourcing for exec search mandates (CTO/VP of Engineering positions), pre-qualifying profiles, preparing long lists. What we're looking for: someone with an affinity for recruiting, clean Excel/Notion hygiene, ideally with some tech understanding (grasping stack terminology; no prior engineering experience required). Reliability > speed. What we offer: market-rate hourly pay for junior research (Germany: ~20-30 €/h), fully remote work, clear briefings, an expected 2-year project pipeline. Write a job ad that works across three channels: 1. A detailed version (250 words) for StepStone / Indeed / working student boards 2. A short version (120 words) for my own LinkedIn profile 3. A WhatsApp message (max. 80 words) I can send to my network Tone: respectful, honest, not sensationalist. A few phrasings may carry a Berlin flavor, but keep it subtle. NO clichés like "go-getter mentality", "rockstar researcher", "hungry for success". We're looking for calm, precise work over at least 12 months.
Personal Decision-making Beginner

9. Think through a hard career decision in a structured way

"Three income streams — dev/tester, danic Sales, precious metals. One probably has to go if the others are supposed to grow. I need clarity before I decide."

Prompt
I'm facing a career decision and need someone to help me structure it — not decide it. My three current income streams: - **Dev/tester** (bread and butter, ~6h/day, secure, but intellectually underwhelming) - **danic.ai Sales** (growth, commission-based, ~2-3h/day, high potential but unstable) - **precious metals content + sales** (side business, ~1-2h/day, slow to build, solid long-term) My conflict: three income streams mean real depth in none of them. One probably has to go. Help me think through the decision systematically: 1. **Three arguments per income stream** for keeping it — and three for why it could go. Please don't be dogmatic. 2. **What intermediate options are there?** (e.g. reduce dev/tester to 30%, pause precious metals for 6 months, wait out the danic Sales phase...) 3. **Which five questions do I need to ask myself** before I decide? Concrete ones, not coaching phrases ("What do you really want?"). Instead: "What earnings mix results in scenario A vs. B after 12 months?" "What happens with health insurance?" "Who is affected if plan A fails?" 4. **One honest observation**: what about my current structure might be an avoidance pattern rather than a rational strategy? Tone: calm, clear, like a sparring partner. You are not my coach. You only structure. I decide.
Sales Research Intermediate

10. Summarize a market study PDF

"I've downloaded an 80-page market study on AI coding tools. I need it as a sales briefing in 5 minutes — usable in my next discovery call."

Prompt (attach the PDF to the chat)
Attached is a market study as a PDF. I work in sales at danic.ai (agentic software engineering) and need a sales briefing, not an academic abstract. Please deliver it in exactly this structure: 1. **Core message in one sentence** — where does the market stand right now, and what has changed since the last report? 2. **Top 5 data points/insights for my day-to-day sales work** — which numbers can I quote in discovery calls starting Monday? (With specific source references incl. page numbers) 3. **Three risks / weaknesses of the study** — what is being debated, which assumptions are open to attack? 4. **A "cheat sheet" table** with the most important numbers (market size, growth rate, adoption rate, ROI ranges, cost comparisons). 5. **Five typical objections/questions CTOs will now ask me more often** — each with a 2-sentence answer building block based on the study data. Stick strictly to the contents of the study. If something isn't in there, say so explicitly instead of guessing. Maximum length: 700 words.

Common beginner mistakes and how to fix them

"The output was nonsense." → You gave too little context
When Claude answers generically, the role, audience, or tone is usually missing. Add it afterwards. Example: "That was too general. Write it for CTOs of mid-sized SaaS companies with engineering teams of around 25 people, with three concrete pointers."
"It was too long." → Set a word limit
Claude tends to answer at length. Say: "Maximum 150 words." Or: "In exactly three sentences." It works very reliably.
"It sounds like AI." → Say what it should not sound like
Negative examples help. "Don't sound like a marketing agency. Avoid words like 'innovative', 'sustainable', 'forward-looking', 'leverage', 'synergy'. Write the way one person talks to another."
"The facts were wrong." → For current facts, enable web search or prompt differently
For current studies, prices, figures, and market data, always enable web search in Claude (icon in the input field) and ask for source references. When in doubt: "If you're not sure, say so. Don't make anything up."
"It assumed too much." → Stop it and ask questions
You can interrupt Claude mid-answer ("Stop.") and re-brief it. Or say right at the start: "Before you answer, ask me three clarifying questions."

Iteration: 70% in one minute → 95% in ten

Don't expect the first answer to be perfect. It rarely is. But with 4–5 short follow-up comments, you'll get extremely close to the target. Example iteration:

Follow-up comments — just type them in
Follow-up comments that almost always work: — "Shorter. Half the length at most." — "More empathetic in tone, less matter-of-fact." — "Less jargon." — "Make it concrete. An example sentence, not theory." — "Write three variants." — "Write it the way a 75-year-old client would understand it." — "Give me the last paragraph again in two versions — neutral and warmer." — "What did you assume that I might see differently?"
The biggest lever

It's not "the perfect prompt". It's the willingness to iterate in 3–4 steps. Once you've internalized that, you've truly understood Claude.

Features · 8 minutes

Projects — your own rooms for recurring topics.

A chat is like a single conversation in an elevator. A Project is like your own consultation room: the same style, the same documents on the table, the same rules — every time you walk in. You don't have to explain everything from scratch each time.

LB
Lukas, after three weeks of using Claude
Consultation appointment · Wednesday, 3:30 PM

"I type the same thing into Claude every single time: 'Reply in the style of my setup, keep it short, informal with clients, always include a note to check back with me, no jargon.' It gets annoying after the tenth time. There has to be a way to store that once."

There is. It's called a Project.

Concept

Chat vs. Project — the crucial difference.

Project

  • For recurring topics ("client communication")
  • Its own instructions, stored once
  • Its own files (e.g. your sales ground rules) — Claude always has them "on the table"
  • All chats inside it follow the same guidelines
  • You open the Project — and get straight to work

Regular chat

  • One-off, isolated questions
  • You have to provide context every time
  • No "library of its own"
  • Every chat starts from zero
  • Good for spontaneous questions, bad for recurring work

Important: within a Project, you still have as many individual chats as you like. The Project is not "one single, never-ending conversation" but a frame in which all conversations share the same ground rules and the same background.

Building

Three building blocks — that's all it takes.

Project instructions ("ground rules")

A text field where you permanently tell Claude how to behave in this Project: role, tone, language, length, formats, no-gos. This is not a one-time prompt — Claude automatically reads these instructions in every chat in the Project. A good project instruction text is 100–400 words long.

Knowledge base ("library")

Files Claude has "on the table" in every chat of the Project: your sales ground rules, your own style guide, FAQs, templates, explainer texts, a vocabulary list. On Pro/Max, large files are automatically made searchable (RAG).

Chats ("the actual work")

Every conversation you have in the Project is saved and visible. You can jump back at any time. Different chats do not share memories, though — every chat starts "fresh" with the background knowledge from building blocks 1 and 2.

One important clarification.

Project instructions are a special form of "system prompt," just scoped to the project. They apply in addition to your profile settings (which apply to everything). If both exist, they complement each other. The profile settings say "this is who I am"; the project instructions say "in this room, I work on X".

Guide

Create a Project — in 4 clicks.

Left sidebar → "Projects"

In the left column, click the Projects menu item (or go directly to claude.ai/projects). You'll see either an empty overview (normal at the start) or your existing projects.

Top right → "+ New Project"

Enter a name ("Client Communication Sales Pipeline") and optionally a description. Both are visible only to you, but have no effect on Claude.

Enter the project instructions

On the Project's main page you'll see an input field labeled "Instructions" or "Set custom instructions". This is where the text goes that we've prepared in the templates below — copy & paste.

Fill the knowledge base (optional, but strongly recommended)

On the right side of the Project's main page there is a "Project knowledge" section. Use the + icon to upload files (PDF, DOCX, TXT, CSV — up to 30 MB per file). Examples further below.

You're in.

Now click into a chat inside this Project. Ask a question that fits the context — and watch how Claude automatically takes your guidelines and files into account without you having to repeat anything.

Templates

Five ready-made Project templates for headhunters & sales

Each template consists of a name, a project instruction (ready to copy), and a suggestion for which files belong in the knowledge base.

Work Project #1

🎯 danic.ai Sales Outreach

For all cold outreach messages, discovery prep, follow-ups, pilot memos, and objection handling. Here, Claude writes the way you would write — if you had unlimited time and always had the danic proof points at hand.

Project Instructions (copy)

Project Instructions
# Role You are my co-author for sales communication at danic.ai. My name is Lukas Bauer, 30, Berlin, headhunter with a dev/tester background, now starting in sales at danic.ai (agentic software engineering, DANIC OS). # Target audience CTOs, VPs of Engineering, Heads of Engineering, and tech CEOs of German mid-sized companies (50–2,000 employees). Engineering teams between 10 and 100 people, in-house product development. Technically grounded, skeptical of marketing speak, value time and proof points. # Style & tone - Clear, direct professional language. No marketing babble, no buzzwords ("innovative", "synergistic", "sustainable", "forward-looking"). - Respectful, but as an equal — I am not a supplicant. - Default: formal address ("Sie"). Informal "du" only if the recipient explicitly offers it or the context is clearly peer-to-peer. - Active voice, not passive. Concrete numbers, not adjectives. - Cold outreach: max. 90 words. Follow-up: max. 60 words. Pilot memo: 1 page. # Content rules - Every cold message ends with ONE clear CTA (20-min sparring session / 15-min call / short question). - With numbers, ALWAYS name the proof point: "LinkedIn Lead Funnel: 92 person-days instead of 4,064 person-days (44× faster), 94% coverage, €174k instead of €4,48M." - Never guarantees ("we will cut your costs by 90%") — always as a range or case reference. - Never name other danic customers unless I provide explicit approval. - No "lock-in" bashing of competitors — differentiate through the USP (stack-agnostic, Complete Handover, no tool selling). # danic.ai core content (always available) - DANIC OS: orchestrated fleet of specialized coding agents (reviewers, testers, architects, refactor bots). 100+ agents in parallel. Stack-agnostic: TypeScript, Python, Go, Java. Runs on the customer's infrastructure — Claude API by default, optionally the customer's own LLM in their tenancy. - USP: No agency lock-in. No tool selling. Complete handover incl. playbooks, pipelines, maintenance. - 3 packages: Pilot (2 weeks fixed price, 1 use case) / Build & Scale (6–12 weeks, 100+ agents, CI/CD, compliance BaFin/GDPR/ISO) / Complete Handover (4 weeks, training for 2–8 engineers, 90-day hotline). - Refs: Cyberport, Siemens Healthineers, Rapha·Med, Porsche Digital, N26 Labs, Deutsche Börse. - Contact: [email protected], Torstraße 138, 10119 Berlin. # Format Standard length per task (above). For memos: clear headings, bullet points, a table where useful. Email sign-off: "Best regards, Lukas Bauer · Sales · danic.ai" — unless I specify otherwise. # What you should always do - Ask follow-up questions when client context is missing (industry, engineering size, current stack, pain). - At the end, briefly flag where you are unsure about the content and what I should double-check in particular. - If unsure about current danic packages or prices: ask explicitly, never invent.

Knowledge base — what to upload?

  • The danic.ai website as a PDF (full content: USP, packages, references, proof points)
  • A "stop words" list of banned terms (marketing junk that must never show up in your outbound)
  • 2–3 examples of excellent cold outreach messages (from you or from other top salespeople, as style references)
  • Optional: an ICP list of your top 30 target companies with a short note on pain points
Work Project #2

📚 Professional Development & Literature Overview

Summarize studies, understand guidelines, compress new recommendations into two paragraphs. Here, Claude becomes your personal, critical editor.

Project Instructions (copy)

Project Instructions
# Role You are my scientific editor and study summarizer for sales-relevant professional development. # My background I am a headhunter, I read English-language studies without difficulty, but with limited time I only want the points that are core-relevant to my sales work. # What I want from you 1. For every study / guideline / publication, a breakdown into: - "Research question in one sentence" - "Method in three sentences" - "Main result" - "What does this mean for a German sales pipeline?" - "What limitations do I see MYSELF as a physician — not the authors" - "Concrete suggested change to my sales work (or: 'No change needed')" 2. ALWAYS cite sources explicitly (author, year, journal). 3. If you did NOT read something in the study but are adding it from your own prior knowledge — say so explicitly. Mark it with "[Note from Claude:]". 4. Never present a recommendation as settled when it is controversial in the literature. # Language & format - English. - Technical language allowed, but precise. - Maximum 400 words per study summary. # Self-check before every reply - Did I make a claim I cannot back up from the source? → flag it or cut it. - Would an experienced headhunter say: "This is relevant to my day-to-day work"? - Did I simplify without oversimplifying?

Knowledge base — what to upload?

  • Market reports and salary studies (Honeypot, Levels.fyi, Robert Half) — as far as publicly available
  • A list of your recruiting focus areas ("Engineering Leadership", "Product/AI Leadership", "FinTech CTOs")
  • Your own notes from past mandates as "vocabulary"
Work Project #3

📣 Personal Brand & LinkedIn Outreach

LinkedIn posts, profile copy, newsletters, cold outreach, pitch emails to clients, precious metals content — you want to come across as a modern, credible professional with three income streams, not like a generic recruiter profile.

Project Instructions (copy)

Project Instructions
# Role You are my co-writer for personal brand and external communication. I am Lukas Bauer, 30, Berlin — headhunter (4 years of candidate search), sales at danic.ai (agentic software engineering), content creator for precious metals investments. # Positioning in one sentence Three income streams, one consistent character: close to tech, honest, no buzzword bingo, with substance instead of a sales mask. # Brand voice - Direct, clear, Berlin tone — polite, but not stiff. - No marketing cliches ("game-changer", "unleash potential", "synergies"). - No exaggerations, no superlatives. - Short sentences. Active verbs. Concrete examples instead of abstractions. - I am not a hype seller — I explain the mechanics and let readers judge for themselves. # What I need, depending on the request - LinkedIn posts (headhunter insights, danic stories, straight talk on precious metals) - LinkedIn profile copy (headline, about, highlights) - Cold outreach to CTOs (danic) and to C-level executives (executive search) - Newsletter emails (precious metals list, danic contacts) - Reels/Shorts scripts for precious metals content (15–60 sec) - YouTube scripts (8–12 min, with timestamps and B-roll notes) - Replies to provocative LinkedIn comments # Content no-gos - No case examples with real candidates or clients without explicit approval. - No guaranteed performance promises ("gold will double in 2 years"). - No direct comparisons with competitors mentioned by name. - Always keep the EU AI Act & GDPR in mind on recruiting topics — ask if a statement is legally borderline. - Never phrase tax or investment tips like professional advice. Always as a personal observation + the note "not investment advice, not financial consulting". # Format - LinkedIn post: 800–1,500 characters, one clear hook in line 1, max. 3 paragraphs, CTA optional. - Reel/Short: max. 90 words, 1 hook within 2 sec, a clear micro-story. - YouTube: offer an outline first, I give the green light. - Cold outreach: max. 90 words, 1 clear CTA.

Knowledge base — what to upload?

  • Your current LinkedIn profile (PDF export)
  • danic.ai website content (PDF) + 1–2 of your best danic posts
  • 3–5 examples of copy from other fields that you like (URL as a note) — as style references
  • A "brand DNA" (10–15 keywords: "close to tech, direct, Berlin, three hats, no buzzword bingo, proof over hype…")
  • A "stop words" list of banned terms
Personal Project #4

🪙 Precious Metals Content & Sales

Reels, YouTube scripts, FAQ maintenance, consultation prep. The Project space where you are not a headhunter, but a content creator and precious metals advisor.

Project Instructions (copy)

Project Instructions
# Role You help me produce precious metals content (Reels, YouTube Shorts, LinkedIn posts, FAQ) and prepare consultation sessions. # My setup - Me (30, headhunter, precious metals sales as a side business) - Target audience: ages 30-55, middle income, wants clarity on retirement planning - Platforms: Instagram Reels (90 sec), YouTube Shorts (60 sec), 1× LinkedIn post/week - Tone: dry and direct, data-driven, slightly counterintuitive — NOT "finance influencer" # Values - Education before selling. Trust is the asset. - No investment recommendations ("You should invest"). Instead: "I choose X because Y." - Tax topics ALWAYS with the disclaimer "not a tax advisor". Refer people to a proper consultation. - No crisis fearmongering, no "gold always goes up", no BS buzzwords. # What I want from you - Concrete suggestions with reasoning, not platitudes. - Per hook: maximum 15 words, a concrete number where possible. - With data: name the source, name the date. If unsure — say so clearly. - Ask if something is missing (target platform, length, tone). # Format - Clearly structured (lists, tables where useful). - Never longer than necessary.

Knowledge base — what to upload?

  • A content backlog with good hooks (from your own Reels, competitors, market events)
  • A note with your recurring topics ("gold ETF vs. physical", "silver tax", "safe deposit box vs. home storage"…)
  • A list of the most common consultation questions with your standard answers
  • A few Reel scripts that performed well (as style references)
Personal Project #5

🏠 Government Offices, Insurers, Contracts

Letters to your health insurer, tax advisor, insurance company. Understanding contracts. Responding to outrageous demands calmly but firmly. The area that drains your energy every Sunday evening.

Project Instructions (copy)

Project Instructions
# Role You are my sober, precise co-author for letters to government offices, insurers, landlords, tax advisors, banks — every party I need to write to in a legally clean, polite, but firm way. # Style - Factual, clear, polite. - Firm, without getting emotional. - Never threatening, never submissive. - Active verbs. Concrete references (date, case number, contract clause). # Structure of a typical letter 1. Brief reference (date, case number, what it's about) 2. The facts in 2–3 sentences 3. What I specifically want (name a deadline if relevant — usually 14 days) 4. Polite closing # What you ALWAYS do - Point out factual errors when I make them in my own description. - Ask me whether I am aware that I am threatening legal action — if the letter is heading in that direction. - Remind me that YOU ARE NOT A LAWYER and cannot give legally binding advice when things get sensitive. - Suggest getting legal advice when it involves money >500 € or unresolved disputes. # What you NEVER do - Threatening gestures, all-caps outrage, exclamation-mark inflation. - Make claims I did not provide in my request. # Format - Standard length: 150–250 words - Structured like a DIN 5008 business letter

Knowledge base — what to upload?

  • Your current letterhead / address
  • A list of the case and contract numbers you regularly deal with
  • A "hall of fame" of your own letters that once worked very well
Lessons Learned

Five rules of thumb for good Projects

1. Better 5 specific ones than 1 big one

One Project per clearly delimited context. "danic sales outreach" and "precious metals content" don't belong in the same Project, or tone and style start to blur.

2. Project instructions are a living document

Update them every 3–5 chats. Whenever you notice "that's not how I want it" — add it to the instructions. This keeps getting better over time.

3. Prohibitions often work better than commandments

"Never jargon without a translation", "Never longer than 200 words" — negative rules like these often work better with Claude than positive guidelines.

4. Keep the knowledge base lean but current

10 clean, well-named files are worth more than 50 chaotic ones. Tidy up every 1–2 months.

5. Never identifiable client and candidate data

Not even in the knowledge base. Create sample files with fictional people. Details in the Privacy chapter.

6. Pro / Max / Team supports RAG

On Pro+, Claude can find what's currently needed even in very large knowledge bases. On Free, the knowledge base is smaller — still enough for beginners.

Features · 12 minutes

System Prompts — onboard Claude, once and for all.

A system prompt is the "job description" for Claude. A kind of onboarding brief for a new employee that tells them: "This is how you work for me. This is the role. These are the rules. This is how I speak. You never do this. You always do that." Written once — permanently effective.

LB
Lukas, after one month with Claude
Wednesday evening · Home office

"There are two kinds of answers I get from Claude. Answers I can use right away — and answers I first have to rewrite into 'my language'. I want only the first kind from now on."

That is exactly what system prompts are made for.

Concept

Three kinds of instructions — and why that matters.

Profile settings

Apply everywhere. This is where you tell Claude who you are and how you work — regardless of topic. Example: "Write concisely, avoid filler phrases, I'm a doctor".

Project Instructions

Apply only within one Project. This is where you tell Claude how to behave for a specific topic — e.g. "client communication". We covered this in the Projects chapter.

Chat prompt

Applies only to this one chat. This is your actual question. It supplements the two levels above without overriding them.

These three levels stack.

Claude always reads all three — profile first, then Project, then chat. That gives you the best of all worlds: permanent ground rules + context-specific requirements + spontaneous request.

Profile settings

The profile settings — your universal system prompt

In the settings at the top right → "What should Claude call you?" and "What should Claude know about you?". This is where the most important text you will ever write goes — it applies to every conversation, every Project, every context. A ready-made template that works well:

Profile setting · applies everywhere
# Who I am My name is Lukas Bauer, 30 years old, Berlin, single. Four years in candidate search, plus a dev and tester background. I'm currently starting as Sales at danic.ai (agentic software engineering), want to break into the executive search game, and in parallel I create content about precious metals investments + sell physical precious metals as retirement provision. # How I want to be addressed - In German, informal "du" form, calm and matter-of-fact. - Not effusive. No "Great question!" openers. - Straight to the point. # How you write for me - Short, clear, structured (short paragraphs, bullet points where useful). - Active verbs, short sentences. - Answer the actual question first, then the reasoning — not the other way around. - If you're unsure about a fact, say so openly. Never make things up. - If something is legally or tax-wise sensitive (precious metals sales, GDPR, EU AI Act, recruiting compliance), point out that my professional review or a lawyer is mandatory. # What you never do - Invent or assume candidate, client, or customer data. - Cite current studies, market reports, or prices if you don't know whether they're real — in that case say "I have no reliable sources on this". - Pay me compliments when there's no answer in them for me. - Use marketing filler words ("innovative", "transformative", "synergistic", "game-changer", "leverage"). # Format standards - Unless I ask for something else: 300 words maximum. - For longer tasks: offer an outline first, only then write it out.
A common beginner mistake.

Do not put project-specific things in your profile settings, like "You are a sales copywriter for danic.ai". Otherwise that also applies when you ask for restaurant suggestions — and Claude will give confused answers. Project-specific content belongs in Project Instructions, not in the profile.

Anatomy

Seven building blocks every good system prompt is made of

You don't have to use all seven. But the more of them you cover, the more precise Claude's behavior becomes. Order within the system prompt: in this sequence.

Role & Purpose

"You are…" — a clear description of the function. "You are my co-author for educational texts in a sales pipeline." Avoid overly generic roles ("You are a helpful assistant" doesn't help Claude).

Audience / Context

Who is Claude actually writing or thinking for? "The recipients are clients between 30 and 80 years old, of mixed educational backgrounds; many read quickly and on the side." Skipping this point is the most common cause of the wrong tone.

Tone & Style

Concrete and enforceable. Instead of "friendly", better "polite but direct; active verbs; sentences under 18 words; no advertising clichés". Better 5 specific rules than 20 vague ones.

Content rules (dos)

What Claude should always do content-wise. "Every cold-outreach message ends with ONE clear CTA." "For every claim about danic proof, always cite the concrete case (LinkedIn lead funnel: 92 person-days vs 4,064 person-days)."

Content taboos (don'ts)

Often more important than dos. "Never give concrete prices without my explicit input." "No performance guarantees." "No precious metals investment recommendations." "Never marketing clichés like 'innovative' or 'transformative'."

Format standards

Length, structure, language. "Standard length cold outreach: max. 90 words. Follow-up: max. 60 words. Pilot memo: 1 page. Email sign-off: 'Beste Grüße, Lukas Bauer · Sales · danic.ai'."

Self-check before every answer

A small "pre-flight checklist" Claude mentally runs through before every answer. "Did I make a claim about danic that I can't back up from the briefing?", "Did I use a marketing buzzword?", "Does the text end with a clear CTA?" — Three questions like these noticeably improve quality.

Meta trick

Claude writes your system prompt — for you.

You don't have to phrase all of this yourself. One of the most elegant applications: have Claude draft the system prompt for you. The following meta prompt — just paste it into a normal chat — gives you a tailored proposal.

Meta prompt · Claude drafts your system prompt
I want your help writing a system prompt that I will then use in the Project Instructions of a new Claude Project. My use case: [HERE you describe in 2–4 sentences what you will regularly do in the Project. Example: "I want to write 5–10 cold-outreach messages per week to CTOs for danic.ai, all in a respectful, technically serious tone, all with a clear CTA. The recipients are technical decision-makers at German mid-sized companies with engineering teams of 10 to 100 people."] Please start by asking me 5–8 targeted follow-up questions that I need to answer so you can draft the system prompt for me. One question per topic area: - Role/purpose - Audience - Tone/style - Content dos - Content taboos - Format - Self-check - Other Don't ask generic questions. Ask questions whose answers will show up concretely in the final system prompt. Only after I have answered all the questions do you deliver the complete system prompt in Markdown format — with clearly numbered sections, ready to copy and paste.
This is exactly the power of Claude.

You provide the context, Claude leads the conversation. After 5–10 minutes of dialogue you have a system prompt that fits you — far better than any generic template. If it isn't perfect, just say: "Tighten point 3, it's too soft for me. Add a point about X." Iteration is part of the method.

Library

Six ready-made system prompts

Each one is ready to use right away. Copy it, drop it into your profile or a Project, lightly adapt it in one place — done.

Work danic Sales

danic.ai Cold-Outreach Copywriter

For all LinkedIn DMs, cold emails, connection requests, and follow-ups to CTOs, VPs Engineering, and tech CEOs of German mid-sized companies.

System prompt · for a Project or as a chat template
# Role You are my co-author for cold-outreach messages and follow-ups in my role as Sales at danic.ai (orchestrated coding-agent fleets, DANIC OS). # Audience CTOs, VPs Engineering, Heads of Engineering, tech CEOs of German mid-sized companies (50–2,000 employees). Engineering teams of 10 to 100 people, in-house product development. Technically well-grounded, skeptical of marketing speak, value time and proof points over adjectives. # Tone & Style - Respectful, at eye level, no supplicant mode. - Default to the formal German "Sie". Use "du" only when the context is clearly peer-to-peer or the recipient has offered it. - Active verbs, concrete numbers instead of adjectives. - Maximum 18 words per sentence. - A hook in line 1 that isn't generic (no "hope you're doing well"). # Content dos - Every cold message ends with ONE clear CTA (20-min sparring session / 15-min call / one short question). - With numbers, ALWAYS a proof point: "LinkedIn lead funnel: 92 person-days instead of 4,064 person-days (44× faster), 94% coverage, €174k instead of €4.48M." - Use the USP points: stack-agnostic (TypeScript/Python/Go/Java), runs on the customer's infrastructure, complete handover, no tool selling, no agency lock-in. - For follow-ups: always reference the previous message without repeating it. # Content taboos - No guarantees ("we cut your costs by 90%") — always a range or a case reference. - No bashing competitors by name (Copilot, Cursor, agency XYZ). - No named danic customers without explicit approval. - Never these words: "innovative", "transformative", "synergistic", "game-changer", "leverage", "synergy", "next-level", "disruptive", "forward-looking". # Format - LinkedIn DM: 70–90 words. - Cold email: 100–140 words. - Follow-up: 40–60 words. - Signature: "Beste Grüße, Lukas Bauer · Sales · danic.ai". # Self-check before output 1. Would an experienced CTO want to keep reading this after three seconds? 2. Is there a buzzword or a guarantee anywhere? → Fix it. 3. Is the CTA ONE clear next step — not a "let's connect"? 4. Did I cite a proof point or just use adjectives?
Work danic Pilot Memo

Pilot memo assistant for discovery follow-ups

Structured 1–2-page memos after discovery calls. Important: all client content anonymized or fictional — real briefings don't belong in consumer Claude. Read the privacy chapter.

System prompt · Pilot memo
# Role You are my co-author for pilot memos and discovery follow-ups at danic.ai. We work exclusively with anonymized or fictional clients — no real company names, no real people. # Style - Matter-of-fact, precise, concise. Like a well-structured strategy memo, not like a sales pitch. - Clear sections with headings. Bullet points where useful, no walls of text. - Tables for comparisons (current state vs. target, effort vs. ROI). - No jargon showcasing — write the way an experienced consultant would phrase it for a technical decision-maker. # Mandatory structure of every pilot memo 1. **Situation** (3 sentences, in the client's own words) 2. **Hypothesis** (1–2 sentences on what a solution would need to deliver) 3. **Pilot scope** (2 weeks fixed price, MVP on the real stack, live demo, architecture report) 4. **What is NOT in the pilot** (clear boundaries — production rollout, training, that's Build & Scale) 5. **Success criteria** (three measurable points) 6. **Investment + comparison** (pilot < 2 weeks of a senior engineer's salary — leave exact prices blank for my check-in with Nicolas/Daniel) 7. **Next step** (a concrete ask: calendar-week start, access to X, workshop date) # Content rules - If I only give you bullet points, propose a complete structure and ask specifically for what's missing. - If client context is incomplete, flag it with "[Missing:]" at the end. - Never insert prices I haven't given you. - Never invent packages or content that isn't in the danic.ai briefing. # Format - Around 400–700 words, fits on A4. - Clear headings, no solid blocks of prose. - Procedure/next steps always as a numbered list at the end. # Taboos - No real company names, people, or stack details from actual discovery calls — even if I enter them (in that case, explicitly check back: "Are you sure this is anonymized/fictional data?"). - No performance guarantees. - No inventions about danic packages, prices, or references. # Self-check - Did I write anything anywhere that sounds like a real client briefing? → Warn. - Is every claim about danic backed by the knowledge base or briefing available to me? - Is the memo directly usable for a technical decision-maker — or does it sound like marketing?
Work Research

Literature & Guideline Summarizer

For weekend professional development. You provide a study or guideline as a PDF / text / link, Claude delivers the sales-relevant summary in half a page.

System prompt · Study reviewer
# Role You are my scientific reader. You read studies, guidelines, and reviews and deliver sales-oriented summaries. # My focus Executive search (CTO/VP Engineering), B2B tech sales (agentic software development), precious metals investments as retirement provision. Relevant topics: engineering leadership, regulated industries (BaFin, GDPR), AI coding trends, compensation benchmarks Series A–C. # Mandatory structure of every summary 1. **Research question in ONE sentence** 2. **Method in three sentences maximum** 3. **Key findings** (bullet points, no more than 5) 4. **What does this mean for my sales or recruiting setup?** (3–5 sentences) 5. **Limitations from a practitioner's perspective** (what the authors miss because they're not in operational sales) 6. **Concrete change proposal**: either "changes nothing" or one specific adjustment 7. **Source reference** (author, year, journal, DOI if available) # Content rules - If I mention a study you don't know, say so openly: "I cannot reliably summarize the exact content of this study." - Never speculate about content you haven't read. - Mark all statements that come from your general knowledge (not from the study) with "[Claude's note:]". - Explicitly flag studies with strong limitations (small sample, sponsorship by an interested party, no operational setting). # Format - German. - Technical terminology allowed, but use it precisely. - Maximum 400 words per summary.
Work Precious metals content

Precious Metals Content Writer

Reels, YouTube Shorts, LinkedIn posts, newsletters — matter-of-fact, no hype, no doom selling, no investment-advisor tone. Honest mechanics explanations for a thoughtful audience.

System prompt · Precious metals content
# Role You are my co-writer for content around precious metals investments (gold, silver, platinum) as a building block of retirement provision. # Audience Working professionals between 30 and 55, with their first savings, who want to understand precious metals as a long-term building block — not as a quick investment. Tech-savvy, equally skeptical of YouTube goldbug screamers and bank representatives. They appreciate mechanics explanations and hate manipulation attempts. # Brand voice - Matter-of-fact, calm, honest. "Personal observation" instead of "investment advice". - Short sentences, active verbs. - Berlin-direct, but polite. - Occasionally actively debunk a myth statement ("gold always rises in a crisis") — that's the core of my brand. - NO hype ("gold at 5,000 within 2 years"). NO doom selling ("cash is being abolished, buy now!"). # Use cases - LinkedIn posts (800–1,500 characters, one hook in line 1) - YouTube Shorts / Reels (60-second script, 1 hook within 2 seconds, a clear microstory) - YouTube scripts (8–12 min, with timestamps and B-roll notes) - Newsletter snippets (4–8 sentences per edition) - FAQ answers for my precious metals customers # Content dos - For claims about prices/mechanics: cite a source or explicitly mark it as "personal observation". - Spread, premium, agio, VAT exemption, speculation holding period (12 months) — always briefly explain these mechanics terms instead of assuming the audience knows them. - For tax-related statements ALWAYS add: "Not tax advice. For specific questions, see a tax advisor." # Content taboos - No concrete performance promises ("gold will double"). - No comparisons with other precious metals dealers by name. - No concrete investment recommendations ("buy 50 grams of gold now"). - No data about my real customers — not even anonymized. - Never these words: "the crash is certain", "last chance", "guaranteed wealth protection", "explodes", "rally". # Format - LinkedIn: max. 1,500 characters, one clear hook, max. 3 paragraphs, optional CTA. - Short: max. 90 words, storyboard structure (hook → mechanics → punchline). - YouTube script: offer an outline first, I give the green light. # Self-check before output - Does this sound like a bank ad or like an honest colleague? - Did I make a claim I can't back up? - Is there a performance guarantee or a doom trigger anywhere? - Could a financial advisor or lawyer issue me a cease-and-desist over this statement?
Personal Travel

Solo Travel Planner

For solo city trips, weekend getaways, workation setups, travel logistics.

System prompt · Solo travel planner
# Role You are my travel planner for solo trips and occasional workations. # About me - 30, Berlin, single. - Usually travel 3–5 days, sometimes as a workation with a laptop. - Like good food (no tourist junk), small bars with music, architecture, occasionally culture (one museum, not five). - Sports: 1 run per trip, happy to have a sauna/pool. - No rental car — light rail, trains, public transit, sometimes a bike. - Mid-range boutique hotels > luxury. # Values - Rather empty half-days for drifting than fully scheduled days. - Quality > quantity. - Reservations for 1–2 restaurants OK, otherwise spontaneous. - For workations: 1–2 reliable coffee work spots + Wi-Fi stability is non-negotiable. # What you do for me - Concrete suggestions with reasoning. No platitudes. - Per suggestion: realistic costs + effort + risk factor. - ALWAYS include a plan B for bad weather. - If you're not sure about availability / opening hours / the current situation, say so clearly — I'll call ahead. - Ask about anything I haven't specified (dates, budget, mode of travel, workation mode or pure travel). # Taboo - No invented restaurants or hotels — only ones you believe actually exist. - If you're not sure: rather give a search recommendation than invent a "suitable hotel". - No price guesses that sound like guidebook level — only ranges ("typically €80–120"). # Format - Clearly structured: overview first, then detail. - Tables for daily plans where useful. - Maximum 600 words per answer, otherwise outline first.
Personal Authorities

Letters to Authorities & Insurers

Matter-of-fact, precise letters — polite but firm. Never threatening, never submissive.

System prompt · Letters to authorities
# Role You are my co-author for letters to authorities, insurers, landlords, tax advisors, banks. # Style - Matter-of-fact, clear, polite. - Firm without getting emotional. - Active verbs. Concrete references (date, file number, contract clause). - Never threatening. Never submissive. - No exclamation-mark inflation. No all-caps outrage. # Standard structure 1. Brief reference (date, file number, subject) 2. The facts in 2–3 sentences 3. What I specifically want (with a deadline, usually 14 days) 4. Polite closing # Mandatory behavior - Point out factual errors in my own description immediately. - If the letter is heading toward escalation (lawyer, lawsuit), explicitly point out that I should seek legal advice. - Remind me that YOU ARE NOT A LAWYER when things get sensitive. - For amounts > €500 or open disputes, advise me to consult a lawyer. # Taboos - Making claims I haven't stated in my request. - Insulting or sarcastic wording — even if I write emotionally. # Format - DIN 5008 business letter - Standard length: 150–250 words - Salutation: "Sehr geehrte Damen und Herren," if I don't give a name; "Sehr geehrte/r Frau/Herr [Name]," if I do - Closing: "Mit freundlichen Grüßen" + my name
Refinement

System prompts are never finished.

Your first system prompt will be okay. Your third will be good. Your tenth will surprise you. Three tips for iterating:

1. Note what annoys you

Every time you have to rewrite an answer — briefly note what didn't fit. After 5 such moments you have 5 new rules for your system prompt.

2. Don'ts are often more effective than dos

"Never use the subjunctive" works better than "write concretely". Negative anchors hit Claude more precisely.

3. Claude improves its own prompt

Say: "Here is my current system prompt. Read it, then show me five concrete weaknesses — and make one improvement suggestion for each."

You now have Claude's most powerful tool.

System prompts are what make the difference between "Claude is a nice toy robot" and "Claude is my most reliable employee". Every good workflow stands or falls with a good system prompt.

Features · 8 minutes

Artifacts — when Claude builds an attachment.

Sometimes Claude answers in the chat. And sometimes a second window opens to the right with a finished document, a checklist, or a diagram — cleanly formatted, downloadable, still editable. Those are Artifacts. They change how you work with Claude.

LB
Lukas, Thursday afternoon
Sales · between two discovery calls

"I asked Claude to build me a pilot memo for a CTO — based on the danic proof points. Suddenly a separate document appears to the right of the chat — formatted, with headings, a table, and a CTA block, ready to download. That was new. And exactly what I needed."

Core concept

Think of Artifacts like an attachment in an email.

In the chat window you talk to Claude — like in a chat. But when Claude hands you a document — a checklist, a letter, a table, a diagram — it doesn't land in the conversation, but in a separate window to the right. That is the Artifact.

Why two windows at all?

So the document stays readable. A twenty-page letter in a chat line would be illegible. A diagram in plain text would be nonsense. Artifacts are Claude's way of saying: "This is no longer a conversation — this is a result. Look at it, change it, download it."

Chat reply

Short, conversational, gets lost in the conversation. Three paragraphs about the pros and cons of a therapy. You read, reply, move on.

Artifact

Standalone document. You can copy it, download it, forward it — and in the next message say: "Make the section on aftercare longer." Claude changes only that section.

Triggers

When Claude creates an Artifact — and when it doesn't.

Claude decides on its own. But there are clear patterns. If your request has one of the following characteristics, chances are high that an Artifact will be created:

Length

The result will be longer than ~15 lines or 1,500 characters. Example: "Write a two-page client letter."

Structure

You ask for a clearly structured document — checklist, table, letter, report. Example: "Create a checklist for the hygiene training."

Reusability

You want to reuse the result later, copy it, or save it as a file. Example: "Make a template for the consent form."

Visualization

You want a diagram, a table, or a process plan. Example: "Show me the therapy process as a flowchart."

You can also request Artifacts directly.

Just write: "Make this a document." or "Create this as a downloadable Artifact." Claude understands that.

Types

Five types of Artifacts that matter to you.

Text document

Pitch memos, reports, LinkedIn posts

This is the most common type. Cleanly formatted with headings, paragraphs, lists. You can download them as Word or Markdown, copy them, reuse them.

Table

Structured lists, comparisons

When you compare or list something — long list vs. short list, salary benchmarks, a danic competitive analysis, precious metals prices over time — you often get a table. Readable, copyable into Excel.

Diagram

Flowcharts, pipeline plans

"Show me the sales funnel from cold outreach to pilot contract as a diagram" — Claude builds a visual schematic that you can embed in a presentation or think through yourself.

Small app / tool

Calculators, quizzes, interactive helpers

Claude can also build simple interactive tools — for example an ROI calculator for danic.ai pitches (senior engineer cost vs. DANIC OS) or a precious metals allocation slider. Usable directly in the browser.

Webpage / layout

Simple HTML pages, templates

For a landing page for a precious metals service or a cover letter with a letterhead — Claude can output a finished HTML page. You see the page rendered on the right, can test it and download it. That's the pro level; to start with, text Artifacts are entirely sufficient.

Six templates

Artifact prompts you can take with you right now.

Copy, paste, adapt. All prompts reliably trigger an Artifact because they are structured enough.

Work Text document

1 — danic.ai pilot memo as an Artifact

A two-page memo you send to a CTO or VP Engineering after a discovery call — structured, without marketing speak.

Copy prompt
Create a danic.ai pilot memo as a separate document (Artifact): Client: [COMPANY, INDUSTRY, ENGINEERING SIZE] Discovery call findings: [BULLET POINTS — e.g. "code review bottleneck, ~40h/sprint tied up"] Stack: [TypeScript / Python / Go / Java] Compliance: [GDPR / BaFin / ISO] Requirements for the document: - Max. 2 pages, A4 - Headings for every section - Factual language (NO "innovative", "transformative", "synergetic") - One concrete number per section where possible Content outline: 1. **Situation** (3 sentences, in the client's own words) 2. **Hypothesis** (1-2 sentences on what a solution would have to deliver) 3. **Pilot scope** (2 weeks, fixed price, MVP on the real stack, live demo, architecture report) 4. **What is NOT in the pilot** (production rollout, training — that's Build & Scale) 5. **Success criteria** (3 measurable points) 6. **Investment + comparison** (pilot < 2 weeks of a senior engineer's salary) 7. **Next step** (concrete ask: start in calendar week X, access to X) Important: Do not insert fixed prices — I will add them after checking with the founder team.
Align with Nicolas or Daniel before sending.

Fixed prices, scope boundaries, and compliance statements must be verified — the pitch is only as good as what the founders can actually deliver in the end.

Work Checklist

2 — SOP checklist for your sales workflow

A reusable checklist — for example for preparing a discovery call, the weekly pipeline review, or onboarding a new client.

Copy prompt
Create a sales checklist as a document (Artifact) for the following purpose: Purpose: [e.g. "preparing a 30-min danic discovery call with a CTO"] Format: - Heading with purpose and a date field - Section "T-24h: Research" (3–5 points: company, stack, recent news, the CTO's LinkedIn profile, shared connections) - Section "T-1h: Preparation" (5–10 points with checkboxes: formulate hypothesis, prepare three discovery questions, have a proof point ready, keep calendar free for follow-up, technical fallback connection) - Section "After the call" (3 points: follow-up < 4h, CRM update, brief Nicolas/Daniel if there is pilot interest) - Signature field: "Completed by: _______ Date: _______" Style: - Concise, one line per point - Concrete, verifiable actions (no "if applicable" or "should") - Printable on A4 or usable as a Notion page
Work Diagram

3 — Sales funnel as a flowchart

A visual process — good for the sparring session with Nicolas, a LinkedIn post about your sales process, or as a self-check to see whether your pipeline logic is consistent.

Copy prompt
Create a flowchart (as an Artifact, Mermaid format) for the following process: Process: [e.g. "handling an inbound lead via LinkedIn — from the first DM to the pilot contract at danic.ai"] Requirements: - Start with "Lead arrives in the inbox (LinkedIn / email / referral)" - Show decision points as diamonds ("Engineering size ≥ 10? Yes/No", "In-house product development? Yes/No", "Budget signaled?") - Maximum 8–10 nodes — otherwise it becomes illegible - Endpoints clearly marked ("End: pilot signed", "End: nurture list 6 months", "End: not ICP") - Labels short, max. 6 words per node Important: This is a rough orientation aid, not a substitute for personal judgment on the call. Please add a corresponding disclaimer at the end.
Personal Text document

4 — Packing list for the solo city trip

A complete packing list sorted by category — created once as an Artifact, adjusted once, and it's ready for the next ten trips.

Copy prompt
Create a packing list as an Artifact document for my solo city trip. Trip: 3 days in Vienna, mid-April, a mix of sightseeing, some sports, 1-2 coffee work spots (I'm bringing my laptop). Traveling by train, hotel with a small gym. Me: - Male, 30, sufficient outdoor experience - Need glasses and headphones for laptop work - Planning 1x running, 1x sauna, otherwise walking / cafe / museum Please organize the list by category: 1. Clothing (based on Vienna weather in mid-April) 2. Tech (laptop, charger, headphones, adapter if needed) 3. Sports (1 running kit, swimwear for the sauna) 4. Toiletries 5. Documents / cards / money 6. "Nice-to-have" (book, notebook, power bank) Per item: a checkbox to tick off. Format: One document, everything printable on one page. As compact as possible — I'm packing for 3 days, not 3 weeks.
Personal Table

5 — Precious metals content plan as a table

Seven days, three channels, with a hashtag and hook column — exactly the thing that's annoying on Sunday evenings, when the week has really already started.

Copy prompt
Create a weekly content plan as a table (Artifact) for my precious metals channel. Context: I'm Lukas, 30, Berlin. My content is factual, no hype, no doom selling. Target audience: 30–55 years old, working professionals with their first savings who want to understand precious metals as a building block of retirement planning — not as a quick investment. Table: - Columns: Day | LinkedIn post | YouTube Short (60 sec) | Newsletter snippet - Seven rows (Monday through Sunday) - Per cell: hook (1 line), core content (2–3 bullet points), CTA - At least 2 days of "myth busting" (e.g. "Why gold doesn't 'always' go up"), 2 days of "mechanics explained" (spread, premium, markup), 1 day of "personal observation" (personal, honest) - No performance promises, no investment tips — everything framed as "mechanics / personal view" Below the table: a consolidated hashtag list (10 items, mixed from large and niche ones) + 5 examples of good hooks to test this week.
Personal Mini app

6 — danic.ai ROI calculator as a mini app

A simple, interactive tool you can demonstrate live in a discovery call. The CTO enters engineering size and hourly rate and immediately sees the savings potential — conservative, of course, and with a clear disclaimer.

Copy prompt
Build me a simple danic.ai ROI calculator as a small, standalone tool (Artifact, HTML/JavaScript). Requirements: - Three input fields: · Engineering team size (number of people, default: 20) · Senior engineer cost p.a. fully loaded in EUR (default: 150,000) · Share of tasks that can plausibly be covered by agentic coding (slider 10–60%, default: 30%) - A "Calculate" button - Output: · Current engineering cost p.a. (rounded) · Conservatively assumed savings in person-days p.a. (based on 220 person-days/year/person) · Conservatively assumed cost savings p.a. in EUR · ROI multiple at a pilot investment of €30,000 (example) - Clear, plain design — dark background (#0a0a0a), white text, one accent in violet (#7c3aed) for numbers - Disclaimer below the result: "Conservative estimate. Actual values depend on stack, use case, and team setup. The real ROI range is determined in the pilot." Works in the browser without an internet connection. One HTML file, everything inline.
You don't have to be a programmer.

Claude writes the code. You see the finished tool right in the Artifact window, can try it out and download it. On a tablet or laptop you can show it live in the discovery call — it lands immediately, because the CTO understands the mechanics.

How to work

Working with Artifacts — editing, sharing, saving.

  1. Improve iteratively

    Just say: "Make the 'Pilot scope' section longer." or "Cut the marketing vocabulary from point 3." Claude changes only what you asked for; the rest stays as it is.

  2. Download or copy

    Via the menu at the top right of the Artifact: download as Markdown, Word, or PDF. Or put the entire text on the clipboard with one click and paste it into your CRM, Notion, or LinkedIn.

  3. Share with a link

    You can also send Artifacts to colleagues via a link. Careful: The Artifact is then publicly visible to anyone with the link — never share candidate- or client-related content.

  4. Reference it in the chat

    You can keep referring to the Artifact in the ongoing conversation: "Write a shorter version of the pilot memo for the LinkedIn DM." Claude knows which document you mean.

Caution

Three pitfalls you should know about.

This works well

  • State clearly what should be in the document — outline, length, target audience.
  • Have it changed iteratively ("rewrite only section 2").
  • Read everything through before sending.
  • Anonymize client and candidate data before entering it.

This goes wrong

  • Forwarding the Artifact to the client's inbox unread.
  • Trusting "it's probably right" for subject-matter content.
  • Passing on Artifact links carelessly (public!).
  • Naming real clients in the prompt.
Artifacts are not a GDPR safe zone.

Everything you write into the prompt — even if the result ends up in the Artifact — is sent to Anthropic's servers. Client data does not belong there. For details, see Privacy & Limits.

You now know Claude's most important productivity feature.

From here on it gets concrete: on the next pages you'll see ten work and ten personal use cases — each with a ready-made prompt.

Use Cases · 25 minutes

Ten use cases for your sales day.

Six danic.ai sales cases, three for your entry into executive search, one for pipeline reflection. Each with a ready-made prompt — ready to copy, adapt, and send.

Three ironclad rules before you start.

1. No real candidate names, current employers, salary data, or NDA-protected client information in the prompt. Always anonymize. 2. Review everything for factual accuracy before sending — Claude gets market data, company insights, and compliance facts wrong. 3. No confidential client or candidate data on the Free/Pro/Max plan. Details: Privacy & Limits.

LB
Lukas, three weeks in with Claude
Friday · 6:30 PM · co-working space emptier than usual

"Cold outreach used to be three hours of adapting templates. Now: discovery prep in 5 min, an email variant in 3, pipeline review at the end of the month instead of the end of the quarter. My conversion limit is no longer time — it's how fast I can explain danic.ai properly."

danic Sales Sales · 15 min

1 — Prepare a danic.ai discovery call

"Discovery call in two hours with the CTO of a mid-sized SaaS company. I need to be prepared — engineering stack, pain points, who has already played around with AI coding."

Before you walk into a discovery call, you don't need a perfect pitch — you need questions that show you understand where engineering hurts. Claude prepares that for you in 5 minutes.

Prompt with web search enabled
Please research the company [COMPANY] and prepare me for a 30-min discovery call with their [ROLE, e.g. "CTO"]. I sell for danic.ai. We build companies their own AI agent development team and hand it over to them completely (no tool resale, no lock-in, stack-agnostic, the setup runs on the client's infrastructure). Give me: 1. **Company snapshot** (4-5 bullets): What do they do, how big is engineering, regulatory situation (GDPR/BaFin/ISO relevant?), latest funding round if findable. 2. **Engineering signals**: Which stack is visible (job ads, GitHub, blog)? TypeScript/Python/Go/Java? Roughly how many developers? 3. **AI traces**: Have they spoken publicly about GitHub Copilot, Claude Code, Cursor, or similar? Is the CTO active on LinkedIn about it? Job ads mentioning "AI experience"? 4. **5 discovery questions** that show my counterpart I understand engineering — no sales questions like "What are your challenges". Instead, e.g.: - "Where does your senior team currently spend most of its time in the code review cycle?" - "If you had 30% less engineering backlog tomorrow — what still wouldn't get done?" 5. **2 likely objections** and how I address them elegantly (without dismissing them). 6. **One concrete hook** from their company (blog post, job ad, LinkedIn update) that I can mention to show: I did my homework. If you're not sure about something: say so explicitly. Better to name a gap than to guess.
danic Sales Sales · 10 min

2 — Cold outreach: LinkedIn message to a CTO / VP Engineering

"Four discovery calls per week — that's the target. Which means: I need 30+ qualified outreach messages every week. Templates burn out; personalization has to scale."

Generic LinkedIn messages get ignored. But personalizing each one manually doesn't scale. Claude helps you build three tonalities — and pick the right one for each recipient.

Prompt for three tonalities
Write three variants of a LinkedIn outreach message (connection request + follow-up message). My product: danic.ai — agentic software development with complete handover. We build 100+ coding agents working in parallel (reviewers, testers, architects) for the client's engineering team, on their stack, and hand over the setup completely. No tool sale, no lock-in, the setup runs on the client's infrastructure. Differentiation vs. GitHub Copilot/Cursor: We are not a coding assistant for the individual developer. We are an autonomous team alongside the team. Speed cases: 44× faster, 26× cheaper (LinkedIn Lead Funnel App: 92 person-days vs. 4,064 person-days, €174k vs. €4.48M). Target person: [ROLE] at [COMPANY]. What I know about them: [BULLET POINTS — e.g. "recently wrote a blog post on code review overhead", "job ad open for 5 senior engineers", "stack is Python+TypeScript"] Please give me three variants: **Variant A — Dry and direct** (for old-school CTOs): No pleasantries. Straight to the point. What we do, what it delivers, whether they have 30 min free. Max. 60 words for the first message. **Variant B — Insight-first** (for tech-savvy VPs): Opens with an observation about their company/industry. Poses a small counterintuitive question. Connection request of 50 words, follow-up message of 90 words. **Variant C — Founder-to-founder** (for founders/solo CTOs): Peer to peer, slightly ironic, no sales gloss. No buzzwords. Max. 80 words per message. Rules for all three: - NO words like "innovative", "disruptive", "synergistic", "transformative", "revolutionary" - One concrete number (44× / 100+ agents / 92 person-days) - One clear, time-boxed ask ("30 min next week?") - No PDF attachments in the follow-up message — link to danic.ai - English or German? German, unless the recipient posts mostly in English
Tip: Set it up as a Project.

Create a Project "danic Outreach" with a system prompt. Then all it takes is: "Variant B for Anna Krause, VP Eng at Acme, insights: [..]" — you save yourself repeating the context.

danic Sales Sales · 20 min

3 — Prepare a pilot proposal — after the discovery call

"Discovery went well. The CTO sketched out a use case (code review bottleneck). Now I need a punchy pilot proposal within 48 hours."

The danic pilot is a 2-week fixed-price engagement with a clear go/no-go decision. For your clients to see the ROI immediately, the proposal has to be tailored to their use case — not feel generic.

Prompt for pilot memo
Create a pilot proposal as a memo (1-2 pages, as an Artifact) based on this discovery call. My product: danic.ai pilot — 2 weeks, fixed price, one concrete use case, MVP on the real stack, live demo, written architecture report. Clear go/no-go decision at the end. Client: [COMPANY], [INDUSTRY] Contact: [ROLE/NAME] Identified use case: [e.g. "reduce code review backlog — 40+ hours of engineering time tied up per sprint"] Stack: [TypeScript / Python / Go / Java / ...] Compliance situation: [GDPR / BaFin / ISO 27001 / requirements for data residency or a self-hosted LLM?] Engagement team size: [N engineers] Memo structure: 1. **Situation** (3 sentences): What you heard in the call, in your own words — so the client can tell you were listening. 2. **Hypothesis** (1-2 sentences): What a solution would have to deliver. If it's wrong — the pilot will surface it. 3. **Pilot scope** (bullets): What the 2 weeks concretely deliver. Architecture sketch, MVP on 1 repo, live test, written report. 4. **What is NOT in the pilot**: Draw clear boundaries. Production rollout, CI/CD integration, training — that's Build & Scale. 5. **Success criteria** (3 measurable points): e.g. "PR turnaround < 4h on 80% of PRs", "0 regressions in the demo suite", "CTO rates the output as 'senior level' or better". 6. **Investment**: Fixed price [insert AMOUNT]. Comparison: a typical senior engineer costs ~12.000 €/month gross; the pilot costs less than 2 weeks of senior salary. 7. **Next step**: A concrete question at the end: "Can we start the pilot in calendar week [X]? From your side, I need access to [Y]." Style: Factual, hands-on, NO marketing language. If something is unclear, phrase it as an open question rather than a claim.
Never quote fixed prices without checking first.

Before you put concrete numbers into the memo, talk to Nicolas or Daniel. Fixed-price pilot ranges vary with use case complexity — a number that's too low locks you in, one that's too high burns the deal.

danic Sales Sales · 5 min to use, 30 min to build once

4 — Objection handling — the cheat sheet

"In the pitch it's always the same three: 'We have Copilot, isn't that enough?', 'What does this actually cost?', 'We can't let externals anywhere near this — compliance.' I need my answers at my fingertips."

Objection handling is 80% preparation and 20% reaction. Build yourself a cheat sheet once with all the classics and the right response to each — Claude delivers the first drafts, you make them your own.

Prompt for objection cheat sheet (Artifact)
Create an objection cheat sheet for my danic.ai sales setting as an Artifact (table). Context: I sell danic.ai — agentic software development with complete handover. We build 100+ coding agents in parallel on the client's stack and hand over the setup completely (no tool resale, the setup runs on the client's infrastructure). Table: 3 columns — Objection · What is really meant · Suggested response Work through these 12 classics: 1. "We already use GitHub Copilot / Cursor — isn't that enough?" 2. "What does this actually cost?" (early stage, no discovery yet) 3. "We can't share data or code externally — compliance." 4. "Sounds like yet another agency that dumps a tool on us." 5. "Who's actually behind this? Never heard of danic." 6. "We don't have capacity for another tool onboarding right now." 7. "Our senior engineers do that themselves, with Claude Code." 8. "Sounds like magic. What's the catch?" 9. "Couldn't we set this up internally instead of buying it?" 10. "We'll wait and see what happens at GitHub and JetBrains first." 11. "Our code is so unique, no AI will understand it." 12. "Send us some materials, we'll get back to you." (= a soft no) For each suggested response: - First briefly validate ("I understand. That's exactly the question we had at Cyberport in the beginning too.") - Then differentiate (not a tool, but a complete setup; no lock-in; runs on the client's infrastructure) - Then make it concrete with a number or a case - End with a question back that opens the conversation — not closes it Style: Like an experienced sales colleague explaining at the whiteboard why you respond this way. No textbook phrases. To the point.
Deploy references as soon as you have them.

danic.ai references (Cyberport, Siemens Healthineers, Rapha·Med, Porsche Digital, N26 Labs, Deutsche Börse) belong in responses to objection 5 ("never heard of you"). Use them sparingly and deliberately — don't run through the whole logo bingo every time.

danic Sales Sales · 5 min

5 — Follow-up after silence — polite but firm

"The CTO seemed interested in the call. Memo sent. Three weeks of silence. The standard move now would be a 'Just checking in :)' — and that's exactly what makes it worse."

Follow-ups after silence are the most common sales discipline and the one botched most often. Most attempts signal weakness. A good follow-up signals value.

Prompt for three follow-up variants
Write three variants of a follow-up email to a client who has stopped responding after a discovery call / pilot proposal. Background: danic.ai. Discovery call went well. Pilot memo sent. No response for [X weeks]. Client: [NAME, ROLE, COMPANY] What was discussed in the discovery call: [BULLET POINTS] What the memo said: [BULLET POINTS] **Variant 1 — Value-add** (no push): There's a relevant insight (article, case, number) on a topic mentioned in the call. You share it without pitching. One sentence of hook, one sentence of insight, one open question. Max. 60 words. **Variant 2 — Seeking clarity** (politely direct): You acknowledge the silence without making yourself small. You clearly offer three paths: a) Let's have a quick call — 10 min is enough. b) Now isn't the right moment — when works better? c) If the topic is off the table — tell me, I won't take it personally. **Variant 3 — Last touch** (closing loop): You close the loop respectfully. "I assume this isn't at the top of the list right now — that's OK. If anything changes, here's my calendar link. Otherwise you won't hear from me again." Clean, no drama. Rules for all: - NO phrases like "Just checking in", "Wanted to follow up again", "Is this still of interest?" - NO new lengthy pitches - NO self-diminishing ("I know you're busy — sorry for bothering you") - Always end with a small, clearly answerable question (or for variant 3: a clean full stop)
Variant 3 is gold.

When you honestly tell a client, "I won't bother you anymore", doors often open that constant follow-ups kept shut. Self-discipline beats pushiness.

Personal Brand Sales · 15 min

6 — LinkedIn personal-brand post on agentic coding

"Sales without visibility is cold outreach in the dark. When CTOs google my name beforehand, they should find something — and see that I understand the topic."

You're not just selling danic.ai — you're also selling yourself. CTOs check LinkedIn before every call. Three good posts per week change the assumptions someone brings into a conversation with you.

Prompt for LinkedIn post with hook
Write a LinkedIn post about agentic coding from my perspective — sales at danic.ai, with a tech background (dev/tester). Topic: [CHOICE — e.g. "Why GitHub Copilot is not agentic coding", "What a 100-agent architecture does differently in 4 weeks compared to 4 senior devs in 6 months", "The most common thinking error CTOs make about AI coding"] Post structure: 1. **Hook in the first 2 lines** — provocative or counterintuitive, but not clickbait. Goal: people click "see more". Examples of good hooks: - "Most CTOs save 2.000 €/month with Copilot and overlook that they're wasting 80.000 €/month because code review doesn't scale." - "I was a recruiter for 4 years. If AI is now replacing engineering teams, why am I suddenly hiring more again?" 2. **Concrete observation / story** (3-5 sentences): from a discovery call, from the stack, from a metric. 3. **One concrete number or differentiation** (1-2 sentences): e.g. "danic cases show 44× faster, 26× cheaper than an average agency — and in the end the setup belongs to the team, not to us." 4. **Takeaway or question at the end** (1-2 sentences): What readers should take away or can concretely answer. 5. **Never**: no emojis at the start, no buzzword bingo, no "What do you think?" filler, no hashtag wall with 15 tags. Maximum 3 hashtags. Style: - Write the way Daniel Deckert or Pieter Levels would write — direct, technically fluent, a bit of Berlin edge. - I'm 30, no PhD. Do NOT write like a consultant. Write like a dev who does sales. - Length: 800-1,200 characters. Tighter is better. - German or English? Depends on the audience — for CTOs in the DACH region, lean toward German.
Pipeline Sales · 30 min once a month

7 — Quarterly pipeline review for yourself

"End of the month. 47 LinkedIn messages, 12 discovery calls, 4 memos, 0 closed deals. The question: is it the funnel, the pitch, me — or is this simply the pace of a six-figure enterprise sale?"

Sales without honest pipeline reflection is gambling. Claude is your sparring partner here — a sober look at your funnel conversion, your weak spots, your levers.

Prompt for pipeline reflection
Be my sales coach. I'll give you this month's numbers — you analyze them soberly, without buttering me up. My numbers (example — adjust): - Outreach sent: [N] - Replies received: [N] - Discovery calls booked: [N] - Pilot memos sent: [N] - In negotiation: [N] - Closed won: [N] - Closed lost (reasons): [BULLET POINTS] My pitch (short version): [4-5 sentences on how I describe danic.ai in a call] Analysis requirements: 1. Calculate **funnel conversion**: outreach → reply → call → memo → negotiation → close. Where is the biggest drop-off? 2. **Industry benchmarks** (state transparently where you take them from): What does a typical B2B enterprise conversion look like for engineering sales (~80k+ deals)? Where am I notably good/bad? 3. **Three likely causes** for the biggest bottleneck — ordered by probability. Don't guess — justify. 4. **Three concrete experiments** for next month. Per experiment: what I test, how I measure it, over what period. 5. **One uncomfortable question** at the end — one I don't ask myself because it hurts. Style: Direct, no padding, but respectful. Like a VP Sales who likes a hire and coaches him honestly precisely because of that.
Monthly, not weekly.

Weekly, the numbers are too small for signal. Monthly gives enough volume for patterns to become visible — without you drowning in data.

Exec Search Exec Search · 30 min

8 — Executive search: build a long list for a C-level position

"First exec search mandate in sight: CTO for a Series B FinTech. The long list is supposed to hold 40 names. I know the market from sourcing, but 'Director Engineering' is not 'CTO with board readiness'."

Long-list building for C-level is not sourcing with a different filter. It's a systematic market scan — who is in which phase right now? Who might be movable? Who is 'on the up'? Claude helps you structure the search.

Prompt for long-list methodology
Help me build a long-list methodology for the following exec search mandate. Position: [TITLE — e.g. "CTO"] Client: [INDUSTRY / SIZE / STAGE — e.g. "Series B FinTech, ~80 employees, Berlin hub plus remote"] Must-haves: [3-5 BULLET POINTS — e.g. "10+ yrs engineering leadership, at least one 50→200 scale-up, regulatory experience BaFin/MaRisk, hands-on at architecture level"] Nice-to-haves: [BULLET POINTS] No-gos: [BULLET POINTS] Please deliver — not the names themselves, but the methodology: 1. **Profile sharpening**: 5 critical questions I should put back to the client BEFORE I build the long list. (What's written between the lines of the briefing?) 2. **Sourcing strategy by bucket**: - Bucket A — "Sitting CTOs at a similar stage" (Where do I look? Which companies?) - Bucket B — "Top VPs Engineering just before the C-level leap" - Bucket C — "Career changers from consulting / founder tracks" - Bucket D — "Comeback candidates" (have done C-level, currently in sabbatical / advisory) Per bucket: typical current employers, search terms for LinkedIn, filter combinations. 3. **Evaluation criteria for long → short**: Which 5-7 dimensions really count (track record, client fit, availability, compensation range, ...)? 4. **Red flags**: What looks good in a profile at first glance but turns out to be a risk on closer inspection? 5. **Fee justification logic**: When the client asks "Why 33% of annual salary for long list + short list + interview support?" — how do I structure the answer? Important: You are NOT my operator. You structure the research, I do it. If you suggest names, mark them as hypotheses, not recommendations.
When searching for candidates: no real names in the prompt.

As long as you're not working in Claude for Work Team/Enterprise with a DPA: NEVER put real candidate names, current employers, salary data, or reference quotes into a prompt — even if it's yours alone. Always anonymize. More: Privacy.

Exec Search Exec Search · 10 min

9 — Executive search: cold outreach to passive C-level candidates

"A sitting CTO at a Series C company in Munich. Earns well, has options. Why would he reply to a LinkedIn message from me?"

Cold outreach to C-level works differently than at director level. Senior people have a finely tuned BS detector — they can tell the difference between someone selling a job and someone curating a career opportunity.

Prompt for exec outreach
Write a cold outreach LinkedIn message to a passive C-level candidate. Client: [COMPANY / INDUSTRY / STAGE] Position: [TITLE] What really makes the position attractive (beyond money): [3 CONCRETE POINTS — e.g. "this company's first C-level position — a mandate to build engineering from 0", "board seat included", "the client is currently becoming the strategic platform for [..]"] Recipient: [ROLE / COMPANY / BULLET POINTS] What I know about the person (publicly): [LINKEDIN INSIGHTS, BLOG POSTS, CONFERENCE TALKS] Message in two stages: **Stage 1 — Connection request (max. 250 characters)**: - No asking "whether I may connect" - One concrete observation that shows I'm not spam-blasting 200 CTOs - Clear positioning: I'm a headhunter, I have a mandate in mind - No promises, no details **Stage 2 — Follow-up message after the connection is accepted (max. 150 words)**: - What it's about (mandate, industry, stage — NO company names without an NDA) - What concretely makes the position attractive (NO salary band, NO location details) - Clear ask: "Up for a confidential 20-min conversation — I'll handle this discreetly, even if nothing comes of it" Rules: - NO phrases like "exciting opportunity", "ambitious position", "unique chance" - NO salaries in the first ping (not even "typical for DACH") - NO pressure ("applications close on ..."), we are not in recruiting - Informal "du" or formal "Sie"? For C-level in Germany: default to "Sie", unless their LinkedIn behavior signals a "du" culture Tonality: - At eye level — we're talking to someone who earns more than we do - Discreet — as if this were about a career decision, not a job - Concrete enough that the person notices: someone actually prepared here
Exec Search Exec Search · 45 min prep, 45 min call

10 — Executive search: reference check guide

"Three reference calls for my final candidate in the CTO search. First one is tomorrow — former CEO, based in Zurich, worked with him for 8 years. I cannot screw this up."

Reference checks separate recruiting professionals from beginners. It's not about ticking off whether someone is a 'top performer'. It's about finding out in 30 minutes whether the person will succeed at this client — or fail.

Prompt for reference check preparation
Create a reference check guide for a C-level candidate. Candidate: [ANONYMIZED — e.g. "Candidate A, currently VP Engineering at a 200-person SaaS company"] Position they are being considered for: [TITLE and stage of the company] Reference giver: [RELATIONSHIP — e.g. "former CEO, 8 years of working together, promoted the candidate from senior to VP"] What I know about the candidate so far: [BULLET POINTS — strengths, risks from the interview] What matters specifically at the client: [3 CONCRETE POINTS — e.g. "must scale engineering from 30 to 100", "must communicate with board members from finance", "must replace a legacy system without a 'big bang'"] Guide structure: 1. **Opening (2 min)**: How do I start — without insulting the reference giver ("obviously you're not going to say anything negative") and without coming across as ingratiating. 2. **Warm-up questions (5 min)**: Three questions that open the reference giver up. Not "How was the collaboration?", but e.g. "If you were starting over with him/her today — what would you do differently?" 3. **Core depth (15 min)**: Seven questions that produce real substance. Ordered: - Concrete situational questions ("Tell me about a decision where you and [candidate] disagreed — how was it resolved?") - Stress questions ("What was the most difficult phase in your collaboration? What did [candidate] do better than others — or less well?") - Scaling questions, matched to the client ("What team size has [candidate] managed personally? Where was the stress limit?") 4. **Risk probing (5 min)**: Three questions that look for weak spots — without sounding accusatory. E.g. "If someone new stepped into your role and inherited [candidate] — what should they be told on day one?" 5. **Closing (3 min)**: One last open question. "Would you hire [candidate] again — and for what role?" Plus thanks, a promise of discretion, a clean wrap-up. Format: table (as an Artifact), columns = Phase · Time · Question · What you watch for Important: Mark three spots where reference givers typically "hide red flags" — and how I uncover them.
Reference checks are a matter of trust.

NEVER enter notes from reference calls into an LLM prompt that isn't running under a DPA. That's not just GDPR — that's professional honor. More: Privacy & Limits.

Ten templates for your sales day.

The first time you use them, each case might take ten minutes — by the third time, three. The time you gain goes straight back into more discovery calls or more precious metals Reels.

Use Cases · 25 minutes

Precious metals, self-management, personal admin.

Four use cases for your precious metals side business, one weekly plan for three income streams, five cases for personal admin. All with ready-to-use prompts.

Precious Metals Content · 30 min once per month

1 — Precious metals content plan for one month

"My precious metals side business lives on visibility. But brainstorming reel topics for an hour every Sunday burns me out. I need a plan, not inspiration."

Content consistency beats content brilliance. A monthly topic plan, aligned with what's currently on your target audience's mind, lifts you out of the daily topic scramble.

Prompt for a 30-day content plan
Create a 30-day content plan as a table (Artifact) for my precious metals investment channel. My positioning: - Precious metals (gold, silver, platinum, palladium) as part of a retirement strategy — not as speculation - Target audience: 30-55 years old, middle income, wants concrete numbers instead of gut feeling, distrustful of "crypto bros" - Platforms: Instagram Reels (90 sec), YouTube Shorts (60 sec), 1 LinkedIn post per week - Sales hook: consulting + selling physical precious metals for retirement Table: Day · Platform · Format · Hook (max. 15 words) · Core message · CTA Requirements: 1. **Topic mix** (across 30 days): - 40% education (market data, history, "What gold really costs once you factor in the spread") - 25% myth busting ("ETFs are not the same thing", "VAT on silver is a trap") - 20% story/personal (no showing off, but insights — storage, choosing a dealer) - 10% news reaction (to major market events) - 5% sales hooks (very sparingly, otherwise it feels sleazy) 2. **Hook rules**: - Never "Did you know that...?" - Never "Warning!" or "Shock!" - Better: "I lost 2.000 € because I bought silver the way you buy gold." Or: "Why I've stopped buying coins right now — and what I buy instead." 3. **Format logic**: - Reels = short, sharp insight - Shorts = data-focused - LinkedIn = longer take with a B2B angle (e.g. precious metals holdings of corporate pension funds) 4. **Seasonality**: - Tax topics January-March - Year-end reviews November-December - "Crisis-proof" mainly during market volatility, not as a permanent hook Style guideline for hooks: dry and direct, data-based, slightly counterintuitive. Not "finance influencer", but "a banker friend explaining something".
Financial content requires care.

Precious metals are an investment asset. Even if you're not a financial advisor in the strict sense — statements like "invest X% in Y" can count as investment recommendations (§ 1 WpHG, German Securities Trading Act). Stick to general education + personal observations. When in doubt, have it checked legally.

Precious Metals Content · 45 min

2 — YouTube video script: 8 minutes of depth

"A good 8-minute video performs better long-term than ten reels. But for that I need a script that doesn't feel like a TikTok in slow motion."

Long-form content builds authority. Reels bring the reach, YouTube keeps people around. The script is the foundation — if the story structure holds, the video holds.

Prompt for a YouTube script
Write a script for an 8-minute YouTube video (long-form, direct-to-camera look). Topic: [CHOOSE — e.g. "Why gold ETFs are not the same as real gold (and when they're enough anyway)" / "The silver tax trap: what you need to know before you buy" / "How I store my own precious metals — and why not in a safe deposit box"] Target audience: 30-55 years old, have savings, fundamentally interested, but not professionals. Tone: Factual, without sales polish, with occasional self-irony. Never "finance bro". Script structure (with timestamps): **0:00 – 0:20 — Hook** No intro with logo animation. Straight in: - One concrete claim that unsettles - Example: "Last month I lost 800 € because I did exactly what 90% of all precious metals channels recommend." **0:20 – 0:45 — Setup** What we'll clear up in the next 7 minutes — and why it's relevant right now (not "because crisis" — be concrete). **0:45 – 4:30 — Main part** Three to four points, each with: - The claim in one sentence - A concrete number or example - What that means in practice - Optional: a common thinking error **4:30 – 6:30 — My concrete setup or my concrete recommendation** What I myself do. With numbers. With providers (where uncritical). With reasoning. **6:30 – 7:30 — Preempt objections** "But what if..." — three common objections, answered honestly, even if the answer is "I don't know for sure." **7:30 – 8:00 — Outro** - What's coming in the next video (series!) - One clear CTA (newsletter / consultation appointment / comment on the video — not everything at once) - NO "smash that like button" Additionally for each section: - **B-roll ideas** (right column): what can be layered in during editing - **Speaking notes** (square brackets): pauses, tempo changes, emphasis Important: - NO investment recommendations ("You should..."). Instead: "I choose X because Y." - NO promises ("will double"). - NO crisis fearmongering.
One disclaimer line at the start saves you comment-section stress.

On-screen text in the first 5 seconds: "Personal opinion, not investment advice." Dry, short, protects you legally, and instantly filters for the right audience.

Precious Metals Sales · 15 min

3 — Preparing a sales conversation — initial precious metals consultation

"A lead from my content is coming in for a 30-minute conversation next week. First consultation, no sales pressure — but I want him to walk out with clarity, not with ten more questions."

A good consultation is 70% listening, 30% setting the frame. Claude helps you prepare the right questions — and frame templates you can use to explain complex topics simply.

Prompt for a consultation guide
Create a 30-minute consultation guide for an initial precious metals conversation. Context: - The prospect typically comes from my reels / YouTube - Age: 30-55 - Has savings (5k-100k €), understands "diversification", wants clarity on physical precious metals as part of retirement planning - I sell physical precious metals, but NOT at any cost — I want fit, not revenue Guide in 5 phases: **Phase 1 — Opening (3 min)** Very relaxed start. ONE question: "What made you start thinking about this now?" My job: listen. Do not mention products. **Phase 2 — Discovery (10 min)** Six questions, in order: 1. "How is your retirement provision currently structured?" (roughly, without demanding numbers) 2. "Have you ever bought physical gold/silver? If so, what was the experience like?" 3. "Being honest — what is your worst case for the next 20 years?" 4. "What matters more to you: short-term liquidity or long-term value preservation?" 5. "How much of this do you want to understand yourself, and how much do you want to delegate?" 6. "What would a good outcome of our conversation today look like for you?" My job: take notes, NEVER switch into sales mode. **Phase 3 — Clarification (5 min)** Three common misconceptions I address WITHOUT coming across as lecturing: - "Gold always goes up" → What 1980-2000 was really like - "Crypto is the new gold" → Function, not performance - "Coins vs. bars" → when which one makes sense Format per misconception: 2 sentences of clarification, one number, one "but". **Phase 4 — Personal recommendation (5 min)** Only NOW a sketch. Format: "If I were in your situation, I would probably..." — NEVER "You should". Three components: - What I would do (with a rough allocation) - What I would NOT do - What I would only observe for 3-6 months first **Phase 5 — Close (5 min, only if it fits)** An honest assessment: - "This makes sense for you today because..." - "This does NOT make sense for you today because..." If not: a clear recommendation for what to do instead. Newsletter? Follow-up appointment in 3 months? A different advisor? Guide format: One A4 page (Artifact), with question markers where I should NOT break the pause too quickly. Important: No sales phrases, no pressure. If the conversation leads to a "not now" — good. Trust is the real asset.
If you want to both advise and sell, you need a clear separation.

If you offer both education and sales, separating the two within the conversation matters. Say explicitly at the start: "Today is a consultation. If at the end we both see that a purchase fits, we'll look at providers. It may also turn out that my offer isn't the right fit — and if so, I'll tell you."

Precious Metals Content · 60 min once, then maintain

4 — Precious metals FAQ as an evergreen sales asset

"The same 20 questions come up in every consultation. 'What about VAT on silver?' 'Should I store in a safe deposit box or at home?' If I answer these cleanly once, those answers save me hours every month."

A good FAQ is a sales asset, not a support document. It answers the questions that lead to a purchase — and filters out the people you're not the right advisor for.

Prompt for an FAQ as an Artifact
Build me a precious metals FAQ as an Artifact (Markdown, printable) with 25 questions — sorted by their order in the customer journey. My setup: - I sell physical precious metals (gold, silver, platinum, palladium) as part of retirement planning - I am based in Germany, customers mostly DE/AT - Target audience see above (30-55, middle income, wants clarity) Structure: 5 clusters of 5 questions each. **Cluster 1 — Fundamentals (5)** E.g.: "Why precious metals at all? Aren't stocks better?" / "What makes gold different from silver as an investment?" / "Gold ETF vs. physical gold — when to use which?" **Cluster 2 — Practical buying (5)** E.g.: "Coins or bars?" / "1 ounce or 1 kilo?" / "Where do you buy reputably in Germany?" / "What is the spread and why is it higher for silver?" **Cluster 3 — Storage & security (5)** E.g.: "Bank safe deposit box — if so, where not?" / "Home safe — sensible or not?" / "What happens in the event of inheritance?" / "Which insurance policies actually apply?" **Cluster 4 — Taxes (5)** E.g.: "VAT on silver — when does it apply?" / "When is gold tax-free at sale?" / "Do I have to declare precious metals in my tax return?" / "Buying anonymously — is that still possible?" IMPORTANT: For tax questions ALWAYS include the disclaimer "I am not a tax advisor" + a concrete referral to their own tax advisor. **Cluster 5 — Selling / liquidity (5)** E.g.: "How do I sell precious metals again?" / "What is the typical resale spread?" / "Does my own dealer accept buybacks?" / "What happens if I need to become liquid and the market happens to be low?" Per question: - One clear 3-5 sentence answer - One concrete number or example where possible - One "but" or "watch out" where relevant - NO sales hook at the end of every answer (max. 3 questions with a subtle CTA) Style: Like an experienced acquaintance who isn't selling anything. Factual, clear, no marketing sound.
Tax questions: don't go it alone.

Even if you know your way around — tax topics belong with a tax advisor. A clear disclaimer per tax question protects you, and as a side effect makes you more trustworthy ("he says what he doesn't know").

Self-Mgmt Self-organization · 15 min per week

5 — Weekly planning with three income streams

"Dev/tester work (bread and butter), danic.ai Sales (growth), precious metals content (side business). Sunday evening I sit down and can already see the week fraying apart. I need a method, not a to-do-list tool."

Running multiple hustles is a time-block battle. Treat everything as equally important and you end up mediocre at everything. Claude helps you structure a weekly prioritization — not make it for you.

Prompt for weekly planning
Be my level-headed planning partner for the coming week. My three income streams: 1. Dev/tester work — pays the rent, ~6h/day committed 2. danic.ai Sales — growth, ~2-3h/day, depends on a successful launch 3. Precious metals content + sales — side business, ~1-2h/day, sporadically sales-oriented Current commitments this week (example — I enter them fresh every week): - Mon-Fri: 4-hour block for dev/tester work (contractual) - Mon 10:00 danic.ai discovery call with [Client X] - Wed 14:00 precious metals consultation appointment - Thu 19:00 sports / personal - Fri evening free Open backlogs (in bullet points): - danic.ai: [LIST — e.g. "3 follow-ups open, pilot memo for Acme not sent yet, LinkedIn silent for 5 days"] - Precious metals: [LIST — e.g. "finish writing the silver-tax reel script, newsletter goes out, new YouTube idea"] - Dev/tester: [LIST — e.g. "Sprint 3 tickets still open, code review for PR #234"] Deliver: **1. Focal point of the week** What REALLY matters this week? If I look back on Friday evening and have gotten ONE thing done, what does it need to be? — Answer this from the logic that danic.ai Sales is currently the lever with the biggest growth opportunity. **2. Time-block proposal (Mon-Fri, as a table)** Columns: Day · Morning · Afternoon · Evening - No day with all 3 income streams at once — at most 2. - Deep work (sales memos, YouTube scripts) in the mornings. - "Reactive work" (emails, follow-ups) in 30-minute slots, not spread across the whole day. - At least 60 min per day left UNplanned ("shock absorber" for the unexpected). **3. Three "if not today, then never this week" tasks** Very concrete, with a deadline down to the day and time of day. Not "do danic outreach" — but "Mon 11:00-12:00: 12 LinkedIn outreach messages to the 'Berlin SaaS CTOs' list". **4. One honest observation** One thing I'm pushing off again this week even though I know it's important. Phrased so it stings, but not demeaning. **5. Recovery check** At least one free evening + 1 sports slot. If these are missing — warning at the end. Style: Direct, brief, no self-optimization language. You are not a coach. You are my planning sparring partner.
Sunday evening is the right time.

If you put 15 minutes into weekly planning on Sunday evening, Monday starts with clarity instead of reactivity. If you start planning on Monday morning, the week is already half lost.

Admin Admin · 10 min

6 — Letter to your tax advisor with multiple income sources

"Three income sources, three types of receipts, one questioning email to the tax advisor per quarter. I need clarity, not ten emails of ping-pong."

Clear emails to your tax advisor save fees and reduce stress. Structure the questions up front — the advisor can answer efficiently, and you don't burn billable consulting hours on clarification.

Prompt for a structured letter to your tax advisor
Please draft a short, structured email to my tax advisor. My setup: - Main employment: dev/tester (wage tax + social security contributions) - Side activity 1: Sales at danic.ai (freelance, fee basis) - Side activity 2: precious metals sales (small-business VAT exemption? still to be clarified) + content (ad revenue YouTube/Insta) Occasion / concrete questions — I provide them as bullet points: [INSERT BULLET POINTS — e.g.: 1. How do I correctly register the side activities? 2. Is the small-business VAT exemption worth it for precious metals? Where is the threshold? 3. What receipts do I need for YouTube ad revenue? 4. Does the danic.ai work count as freelance professional work or as a trade business? 5. When are the advance tax payments due?] Requirements: - Salutation: "Dear Ms./Mr. [Name]" - One line of context at the top: "Background: three income sources since [DATE]" - Questions numbered (in the order I provide them) - Per question: at most one piece of follow-up information that could be relevant for the answer - One concrete request at the end: preferred way to reply, desired timeframe, openness to a 15-minute call as an alternative - Closing: "Kind regards, Lukas Bauer" - Max. 200 words Style: Polite, clear, no small talk. No emotional language. Make sure my tax advisor can give all the answers in a single reply email.
No bank details, tax ID, or account balances in the prompt.

My standard: placeholders like [AMOUNT] / [DATE] / [TAX ID]. I add the real numbers to the finished letter myself. Never through the LLM API.

Travel Personal · 15 min

7 — Planning a solo city trip — compact, without family

"Three days off, I want to get away. Alone. Some city, some sport, some winding down. Not in Berlin, not far away, no hostel."

Solo trips are different from family vacations — the plan needs to be more flexible, but at the same time you don't want to spend an hour in the hotel lobby researching restaurants.

Prompt for a 3-day solo trip
Plan a 3-day solo city trip for me. Key facts: - I start from Berlin - 3 full days (Friday-Sunday), arriving Thursday evening, returning Sunday evening - Solo, 30 years old, male, up for: - Moderate sports activity (running, walking, swimming) - 1-2 good restaurants per day (not expensive, not hipster-overdone) - 1 museum or exhibition - Coffee spots for working (I'm bringing my laptop) - Some contemplation — not a party trip - Budget: [AMOUNT] total incl. travel and hotel - Destination region: [CHOOSE — e.g. "Hamburg" / "Vienna" / "Prague" / "Copenhagen" / "Milan"] Plan format: 1. **Getting there** (train or flight — which makes more sense?) 2. **Accommodation**: 3 concrete suggestions in different districts, each with an argument (location, atmosphere, price) 3. **Daily plan** (Fri-Sun): - Morning (with a sports slot) - Lunch (restaurant tip) - Afternoon (culture OR a coffee work spot) - Evening (restaurant tip or bar) 4. **Coffee spots** for laptop work: 5 concrete locations, noting whether they have Wi-Fi/power outlets 5. **Swimming or jogging**: concrete routes or indoor pools 6. **One 'if I feel like going deeper' alternative**: a day trip or a special activity if I want more Important: - NO tourist classics I can get from any guidebook - Concrete restaurant names with a short reason (who it's a fit for) - If you're unsure (opening hours, whether a restaurant still exists) — say so OPENLY. Better 5 real recommendations than 10 possibly dead ones. - Format: table as an Artifact, plus a short prose intro per day (3 sentences)
Admin Personal · 10 min

8 — Car sale listing for mobile.de

"My old car has to go. I don't want a dealer's price. But private listings usually look like 'selling in a hurry, no questions please.'"

A factual, complete listing sells faster and usually for more money than terse "or best offer" texts. Claude structures the listing — you fill in the real data.

Prompt for a sale listing
Please write a car sale listing for mobile.de. Vehicle: - Make / model / type: [e.g. VW Golf 7 GTI, manual transmission] - First registration: [month/year] - Mileage: [current reading] - Color exterior / interior: [...] - Equipment: [highlights — navigation, heated seats, tow hitch, etc.] - Condition: [honest — e.g. "good overall condition, one small dent rear right, all inspections done, brakes replaced 6 months ago"] - Service booklet: [complete / gaps] - Accident-free: [yes/no] - Inspection (HU) valid until: [month/year] - Tires: [summer tires mounted, winter set included? tread depth?] Price: [negotiable? fixed price?] Listing structure: - Attention-grabbing title (max. 65 characters) - Short description, 3 sentences - Bullet points: key facts - Bullet points: equipment - Bullet points: condition (name the flaws honestly too — builds trust) - Standard boilerplate at the end: "Test drive by arrangement, no guarantee/warranty, private sale, viewing in Berlin" Style: Factual, complete, honest. No exaggerations. If you're unsure about any detail — mark it with [PLEASE VERIFY] so I don't leave anything incorrect in the listing.
Admin Admin · 5 min

9 — Letter to your landlord or a government office

"I have a concrete question / a concrete request — and I notice once again that it takes me hours to write a usable letter."

Correspondence with government offices and landlords follows a simple structure. Facts first, request concrete, deadline clear. Claude cuts this down to 5 minutes.

Prompt for a formal letter
Please write a short, formal letter to [LANDLORD / PROPERTY MANAGEMENT / GOVERNMENT OFFICE]. Recipient: [name or "Dear Sir or Madam"] Occasion: [concrete — e.g. "Request to sublet for 4 months from July 1 due to work-related absence" / "Reduction of the utility advance payments due to multi-year credit balances" / "Registration of a secondary residence"] Content bullet points (in the order they should be addressed): 1. [e.g.: contractual relationship and address] 2. [e.g.: concrete occasion] 3. [e.g.: what I am specifically requesting / communicating] 4. [e.g.: deadline by which I need a reply] Style: - Polite, but direct - Structured (points 1-4 numbered if there are more than 2 matters) - One concrete request at the end (callback? appointment? reply by email?) - Length: max. 200 words - Factual language, no filler phrases at the start - Salutation + closing appropriate to the type of recipient Format: DIN 5008 business letter, output as an Artifact with letterhead placeholders at the top (name, address, date).
Always include a deadline.

Government offices and landlords respond faster to clear deadlines. Example: "I would appreciate a reply by March 15, as I would need to sign the sublease agreement with the subtenant by then." Concrete beats politely vague.

Fitness Personal · 15 min once per month

10 — Weekly fitness plan: strength training + cardio + recovery

"Three income streams, long days, a desk job. If training becomes yet another task, it all tips over. I need a plan that fits me — not a bodybuilder."

A fitness plan that doesn't work out is usually too ambitious. Better three realistic sessions per week done reliably than six ambitious ones with two weeks of discipline and three weeks of skipping.

Prompt for a realistic weekly training plan
Create a 4-week training plan for me that fits my everyday life. My setup: - 30 years old, male - Desk job, ~10h/day at the desk - Goal: general fitness, some muscle building, good posture — NO competition - Current state: occasional running (5-8 km), little strength training for ~1 year - Available training days: 3-4 per week, 45-60 min each - Equipment: gym around the corner (standard machines + free weights) - Realistic time budget: 3× per week guaranteed, 4× if the week is relaxed - No injuries, but my shoulder acts up sometimes (desk posture) Requirements: 1. **Weekly structure** (4 weeks, with progression): - Table: Day · Focus · Exercises · Sets × Reps · Notes - Week 1: light — acclimatization, technique - Weeks 2-3: slight progression - Week 4: deload (somewhat lighter, before a new cycle) 2. **Exercise selection**: - Compound-focused (squats, rows, shoulder press, lat pulldown, bench press) - Per session: 4-5 main exercises, max. 2 isolation exercises - One mobility component per session (shoulders, hips) - NO complicated exercise variations — basic lifts, done cleanly 3. **Cardio**: - 1× running 30-45 min (weekend) - On strength days: max. 5 min warm-up, no additional cardio 4. **Recovery**: - At least 1 rest day between strength sessions - Name a minimum sleep target (8h realistic) 5. **Three anti-fail rules**: - What do I do on days I can't make it to the gym? (bodyweight backup, max. 20 min) - What do I do when I feel my shoulder? - What do I do if I skip 2 weeks (illness, travel)? 6. **Measuring points**: - 3 concrete markers that show me progress after 4 weeks (weight increase on 1-2 main lifts, subjective energy, a photo comparison) Style: Factual, no "no pain no gain" talk. If something is uncertain (e.g. the shoulder — what would really help is a physio check) — say so openly. Format: table Artifact with the 4 weeks, print-ready. Plus 5 sentences at the top: "What I'm learning this month" — not "What I'm achieving".
AI is not a trainer.

A training plan from Claude is a good starting point — not medical advice. If you have preexisting issues (knees, back, shoulder), a physio or trainer belongs in the picture. Claude can help you formulate the right questions for that appointment.

Twenty templates for your everyday life.

These ten plus the ten on the Sales page cover most of your weekly writing and planning work. Bookmark this page — you'll need it more often than Notion.

Required Reading · 18 minutes

Privacy, GDPR, and the limits of Claude.

This page is not optional. If you work with Claude in sales, in headhunting, or with precious metals content, you are responsible — for the data, for the accuracy, for the consequences. This page tells you what you need to know. Clear, without legal jargon, but precise.

The one rule that carries everything:

Never enter real candidate, client, or customer data into the consumer versions of Claude. Free, Pro, and Max are not intended for personal B2B data — not even "just briefly", not even "just this one candidate". Period.

LB
Lukas, after the first scare
Wednesday evening · the message from the client has arrived

"I had the idea of having Claude write a candidate pitch for my client — after all, I had only entered the current employer, the position, and a few keywords, no name. But: senior engineering manager + current employer + Berlin tech scene = that is effectively identifiable. Client and candidate data is more than just name and date of birth. That was an important lesson."

Plan Comparison

Which Claude plan is suited for what?

Anthropic offers different plans with different contractual assurances. For use with client, candidate, or customer data, the difference is existential.

Free, Pro, Max

Personal accounts. No data processing agreement (DPA) available. These plans are aimed at private individuals and general use.

Unsuitable for client, candidate, and customer data. Even if you turn off training (which you can — see below), there is no contract that meets the GDPR's requirements for a data processor.

Allowed: Anything without personal data — generic sales copy, marketing, outreach templates, research on public companies, precious metals content, personal matters.

Claude for Work (Team, Enterprise)

Business accounts with DPA option. For these plans, Anthropic offers a data processing agreement (DPA — Data Processing Addendum) plus additional security and compliance options.

Even here: The DPA alone does not automatically make use with client, candidate, and customer data permissible. You also need your own data protection impact assessment (DPIA), sign-off from a DPO, and, sensibly, a restriction to clearly defined use cases.

Recommendation: If you want any client or candidate reference at all, Team/Enterprise is the minimum.

This information is guidance, not legal advice.

Terms, contracts, and options change. Before you set up a business account, have your data protection officer review the current contract terms and the supplementary guarantees from Anthropic.

Data Flow

What happens to your inputs?

  1. Transmission to Anthropic's servers

    Everything you type into the chat — and every file you upload — is transmitted in encrypted form to Anthropic's servers. Anthropic is a US company headquartered in San Francisco. Server locations and sub-processors follow from the current state of the contract documents, which are updated regularly — ask your DPO for the versions currently in force.

  2. Processing by the model

    The model processes your input and generates a response. During this processing, your data is briefly present in the working memory of the servers.

  3. Storage of the conversation (chat history)

    Your chats are stored in your account so that you can refer back to them later. You can delete chats — that deletes them in your account. How long they remain on the servers in backups or logs is governed by the contract.

  4. Training: Off by default, but verify

    Anthropic states that inputs from consumer accounts are not used to train the models without explicit consent. In the settings, a corresponding option is usually switched off by default. Verify this in your account: Settings → Privacy → Help improve Claude. Switch it off deliberately — and document it in writing.

Even in the "training off" state, your inputs have not disappeared.

They are just not baked into future model versions. But they sit on US servers. They are technically accessible — to Anthropic, to sub-processors, and in the extreme case to US authorities under the CLOUD Act. That is the basis for the strict rule above.

Red Lines

What you must never enter.

This list is not exhaustive — but if any of it applies, one thing is clear: not into Claude.

Personal candidate & client data

  • Name, date of birth, address
  • Full CV as a PDF with identifiable details
  • LinkedIn URL, phone, email
  • Photo, passport / ID
  • Current employer + position + location (effective identification)

Confidential B2B data (clients / danic.ai)

  • NDA content (Cyberport, Siemens Healthineers, etc.)
  • Original client briefings with company names
  • Pricing negotiations, discount tiers, fixed-price calculations
  • Indirect identification too (industry + engineering headcount + location + news event)

Your own sensitive data

  • Passwords, PINs, API keys
  • Bank details, account statements
  • Tax IDs, social security
  • Confidential material from ongoing proceedings

Precious metals business

  • Customer list with amounts or order history
  • Supplier terms, spreads, margins
  • Confidential correspondence with precious metals customers
  • Bank account details, wallet addresses
"But I left out the name!"

Often not enough. A "47-year-old senior engineering manager from Berlin, currently at a DAX-40 fintech, with a cloud migration background" is effectively identifiable — even without a name. GDPR-relevant is anything that can identify a "natural person", alone or in combination. The rule of thumb: When in doubt, it counts as personal data.

Anonymization

Anonymizing — how to do it right.

For many tasks you don't need real client or candidate data at all. You need the structures. Here is how to phrase requests without making people identifiable:

Not like this

  • "Write an outreach message to Anna Becker, VP Engineering at Acme GmbH, Berlin, born 1984…"
  • "Assess this profile: candidate M.K., 38, currently CTO at N26, earning 220k € according to the application…"
  • "Here is the client NDA from Cyberport — can you analyze the contract clauses for me?"

Better like this

  • "Write an outreach message to a typical VP Engineering at a mid-sized SaaS company — placeholders [NAME], [COMPANY], [STACK]."
  • "Assess in general terms the profile of a Series B CTO with 10+ yrs of experience — when is 220k € total comp in line with the market, when above/below?"
  • "Here is an anonymized sample NDA (markers such as [CLIENT], [CANDIDATE], [DATE]) — which clauses are critical for me as a headhunter, which are uncritical?"

The three anonymization techniques

Technique 1

Placeholders

Copy the original text and replace personal references with markers: [NAME], [DOB], [ADDRESS]. The markers remain in the result — you fill in the real data manually only at the very end.

Technique 2

Generalization

Instead of "client K.M., 67, from Berlin, with X", say "a 65-year-old client with X". Specific identifiers out, the clinical constellation in.

Technique 3

Hypothesizing

"Imagine the following case: …" — that turns a concrete case into a teaching example. The model responds to the example; your clinical reality stays out of it.

Most tasks don't need real data at all.

A cold outreach template is generic. A sales memo skeleton is generic. A market analysis summary is generic. Candidate or client data is almost never necessary — it only creeps in because we are used to thinking in concrete terms.

Professional Limits

Hallucinations — when Claude is confidently wrong.

Claude is a language model. It generates plausible text based on statistical patterns in training data. It does not know anything in the human sense. That has a specific consequence: sometimes Claude invents facts. Very convincingly.

Classic hallucination risks in your day-to-day work:
  • Invented study/market report citations ("Gartner 2025: 73% of CTOs use agentic coding…") — with source, year, page, all completely made up
  • Wrong danic.ai prices or package contents (always verify with Nicolas/Daniel)
  • Wrong EU AI Act dates or GDPR fine thresholds
  • Invented candidate salaries / market benchmarks ("Senior Engineer Berlin: 95k €" — what source is that based on?)
  • Wrong tax statements around precious metals sales, the speculation holding period, VAT on investment gold
  • Invented LinkedIn profiles, company structures, or reorganizations

How to spot hallucinations

  1. Strikingly specific citations

    If Claude gives you a study with author, journal, year, and page — and it sounds important — google it. Only then quote it or act on it.

  2. Answers that are too smooth for hard questions

    Complex sales, recruiting, or investment questions often have no single clear answer. If Claude still sounds like "The recommendation is…": get skeptical.

  3. Specific numbers without context

    "The ROI rate is 73%" — where does that number come from? From which study, which market, which sample? Ask.

  4. Confidence is not an indicator of correctness

    Claude phrases wrong statements just as confidently as correct ones. You cannot infer correctness from the tone of the response.

Protective sentences for your system prompt:

— "For factual claims, always state the level of uncertainty: 'established' / 'likely' / 'unclear'."
— "If you are unsure about a source, say so openly instead of guessing."
— "Never invent study citations, market reports, or prices. Prefer 'I don't have a specific source for this'."

Law & Breach of Contract

Your responsibility remains — in full.

Even if you use Claude for preparation, for research, for writing — the legal and contractual responsibility for what reaches your clients, candidates, or precious metals customers stays with you. Always.

Breach-of-trust risk

If a client finds out that you fed their NDA-protected briefings or pricing negotiations into an AI system without contractual protection: mandate gone, reputation gone. In the headhunting market with its small circles, one case is enough.

NDA breach (civil law)

If you pass content under NDA (danic clients, precious metals suppliers, executive search briefings) to an unauthorized tool, that can be a contractual breach — with contractual penalties and damages. Unlike § 203 StGB for physicians it is not criminal law, but economically often harsher.

GDPR fines

A GDPR violation carries fines of up to 20 million euros or 4% of annual revenue (for solo entrepreneurs typically far less, but four to five figures are realistic). On top of that come possible damage claims from individual data subjects.

EU AI Act in recruiting

As of August 2, 2026, recruiting tools count as high-risk AI applications. If you use Claude for candidate preselection or structured profile ranking, you fall into this category — with transparency, documentation, and human oversight obligations. See the section below.

Treat Claude like a very diligent junior sales intern in her first month.

You get many things faster and better. But proofreading, checking, signing off — that is on you. Always.

Regulation

EU AI Act — what you need to know from August 2026.

The EU AI Regulation (EU AI Act) has been in force since August 2024 and takes effect in stages. Most general obligations for organizations using AI apply from August 2, 2026. For recruiting / staffing, this is especially relevant — these applications are explicitly classified as high-risk AI.

Recruiting = high-risk

Annex III of the AI Act explicitly lists "employment, workers management and access to self-employment" as a high-risk area. AI systems used for recruitment, selection, evaluation, filtering, or promotion fall under it — even if Claude "only" helps with profile screening, ranking, or building the long list.

Transparency obligations

Candidates must be able to tell when AI was involved in the selection process. AI-generated texts that go to candidates (outreach messages, rejections) should be identifiable as such — the legal line here is still in motion.

Human in the loop

For selection and evaluation decisions, "human oversight" is mandatory. An AI must not make a hire/no-hire decision autonomously or prepare it on its own — you have to review, approve, and take responsibility.

Documentation & bias testing

Anyone using AI substantially in recruiting has documentation and bias-testing obligations. Which ones exactly, and above which threshold, is being spelled out in guidance from the supervisory authorities. Rule of thumb: If you use it regularly, document it.

The AI Act is still in flux at the detail level.

Much of it is being fleshed out through implementing regulations and guidelines from the EU and the national supervisory authorities. Keep an eye on the topic — via your DPO (if you have one), a lawyer specializing in IT law, or industry associations such as BPM (Bundesverband der Personalmanager) or BDU (Bundesverband Deutscher Unternehmensberatungen).

Pre-Use Check

Ten-second checklist before every use of Claude.

Train yourself to run through these five questions mentally before every prompt. After two weeks it becomes automatic.

  1. Is there personal data in it?

    A name, a date of birth, a LinkedIn URL, a current employer + position + location, a rare combination of skills + tenure + industry — anything that makes a specific person identifiable? If yes: STOP. Anonymize or don't enter it at all.

  2. Am I on the right plan?

    Anything involving personal data or NDAs only in Claude for Work with a DPA and after DPO/lawyer sign-off. Generic work can go in any plan — as long as there is no personal data.

  3. Have I disabled training?

    Settings → Privacy → "Help improve Claude" → off. Check it once, and you're done.

  4. Do I understand what Claude will answer?

    If you cannot judge the topic professionally, you cannot judge the answer either. In that case, Claude is the wrong tool for the job.

  5. Do I have a strategy for verifying the answer?

    Comparison against a guideline? Cross-check with colleagues? Your own expertise? If the answer can have patient-related consequences, it must be verified before you act.

When to Involve the DPO

When should you consult a DPO or lawyer?

Always involve them when:

  • You are setting up a Claude business plan (Team/Enterprise)
  • You want to use Claude in a process in which candidate, client, or customer data could appear
  • You are building or updating your record of processing activities (ROPA)
  • You need a DPIA (data protection impact assessment) (almost always relevant for recruiting AI)
  • You are unsure whether a specific use is permissible — especially under the EU AI Act from August 2, 2026

Usually not necessary when:

  • You use Claude privately (vacation planning, a letter to your tax advisor)
  • You do sales tasks without personal data (generic cold outreach template, LinkedIn post about danic, general market analysis)
  • You produce precious metals content without specific customer data
  • You do general professional development with no reference to specific individuals
If you are a solo entrepreneur without a DPO:

Solo headhunters and sole proprietors are often not required to appoint a DPO (that depends on headcount and data processing), but they carry the responsibility themselves. In that case: get external advice before you use Claude in candidate- or client-related workflows. There are specialized privacy consultants for HR/recruiting, often referred through the industry associations BPM (Bundesverband der Personalmanager) or BDU.

You have the most important part behind you.

If you internalize the pre-use checklist, work in the right plan, recognize hallucinations, and keep hold of your own responsibility, you can use Claude safely and productively. Privacy is not an obstacle — it is a routine you will internalize quickly.

Onboarding · 10 minutes

Ready to go in 10 minutes.

You need three things: a browser, an email address, and five minutes of uninterrupted time. This page walks you linearly from login to your first productive result. No technical background required — just a little patience with yourself the first time.

LB
Lukas on a Wednesday evening
Headhunter · after the consulting appointment

"I just poured myself a glass of wine. I'm opening Claude. I haven't done anything yet. Tell me exactly what to click — and what to type, so that after 10 minutes I know whether this is worth it for me."

Step 1 · Account

Create an account — like an email address, only in 90 seconds.

You do this once. After that, you just log in next time — exactly like on any other website.

Open claude.ai in your browser

Type it into the address bar of Chrome, Safari, Firefox, or Edge. You'll land on a start page with two buttons: "Sign up" and "Log in". If this is your first time there, click Sign up.

Sign up — easiest with Google

You can register with any email address. If you have a Google account (Gmail, Google Workspace), click "Sign in with Google" — one click, done. Alternatively, go the classic route with an email address plus a password of your choice.

Confirm your phone number

Claude asks for your mobile number once to prevent spam accounts. You'll receive a 6-digit code by SMS, enter it — that's it. Your number won't be used for anything else.

Enter your date of birth & name

A few required fields to confirm you're of age and for how you'll be addressed. For the name, your first name is enough — you're talking to Claude, not a registry office. You can change this name at any time later.

You're in.

You'll now see a white chat window with a friendly greeting and a text input field at the bottom. That's all. This is where all the magic happens.

Free to try.

The Free plan is completely sufficient for what you'll do today. You can chat for several hours before you even hit a limit. Payment comes later — and only if you really need it. More on that below.

Step 2 · Orientation

The interface — three areas, nothing more.

Don't get distracted by buttons you don't need today. These are the three areas you need to know:

1. Text input field

At the bottom center. This is where you type or paste your question. Enter sends, Shift+Enter adds a line break. Everything happens here.

2. Left sidebar

Your history. Every chat you've had stays saved there. You can come back to it at any time. One click on "New chat" starts a fresh conversation.

3. Your initials (top right)

This is where you get to the Settings: change your plan, profile details, privacy options. You only need this once today — we'll go there in step 4.

Forget everything else.

There are a few more icons — for projects, artifacts, models. They come later. Today you'll only use the text input field. Really.

Step 3 · Your first conversation

Write your first prompt.

Let's make it sporting. Three tasks that will deliver a real aha moment within the next 5 minutes. Simply copy each prompt, paste it into the input field, press Enter — and watch what happens.

Test 1 — Explain danic.ai in one sentence

First test · 30 seconds
Explain danic.ai in a single sentence so that a VP Engineering (50 engineers, knows GitHub Copilot) immediately understands the difference. Avoid marketing language. NO words like "innovative", "transformative", "synergistic". Concretely: danic.ai builds companies their own AI agent development team of 100+ coding agents (reviewers, testers, architects) on their stack and hands it over completely — no tool sales, no lock-in. Give me three versions to choose from.

Test 2 — Draft an email

First test · 30 seconds
Draft a short, friendly but firm LinkedIn message to a vendor (recruiting SaaS) I want to turn down politely but clearly, because my sales workflow has no room for new tools right now. Thank them for the demo request, offer to take another look in 6 months if a concrete need arises — but without any backdoor that sounds like "maybe after all". Salutation: "Hi [first name]". Signature: "Best regards, Lukas".

Test 3 — Something personal: restaurant suggestions

First test · 30 seconds
Suggest three restaurants in Berlin for a date on Saturday evening: upscale cuisine, but no Michelin-star temple. Italian or Mediterranean. Good wine list. A reservation should still be possible two days in advance. Briefly explain for each restaurant why it might be a good fit. If you're unsure about opening hours or the current situation, say so explicitly — I'll call them myself.
Done? Congratulations.

You've just seen in three areas — sales explanation, polite decline, everyday personal life — what Claude can do for you. Now let's set up a few settings so all of this keeps working well for you in the long run.

Step 4 · Settings

Three settings you set once today.

Click your initials in the top right, then Settings. Three tabs are important:

Profile settings → "What should Claude call you?"

Enter your first name and briefly what you do. Example: "Headhunter with a dev/tester background, 30, Berlin. I'm just starting as Sales at danic.ai (agentic software engineering), want to get into the executive search game, and am building precious metals content on the side." Claude will then tailor its answers to you better.

Privacy → Set training to "Off"

In the Privacy tab you'll find the option for whether Anthropic may use your chats to train new models. Set it to Off. That way your inputs won't end up in future training data. (On the Free plan this matters. On Team and Enterprise it's disabled by default anyway.)

Appearance → Dark mode (optional)

Easier on the eyes, especially in the evening. A matter of personal taste. No effect on functionality — just on your eyes.

Important — even with training turned off:

Real client and candidate data still never belongs in Claude (at least not in the consumer plans Free/Pro/Max). Anthropic is a US provider, and no GDPR data processing agreement is available on the Free plan. For professional use involving client data, you need Claude for Work (Team/Enterprise) with a DPA or a different provider. Read the privacy chapter.

Step 5 · Plan

Which plan — and when?

Start on Free. Period. After two to four weeks of use, you'll know for yourself whether to upgrade. Here's an honest, brief overview (as of 2026):

Free — €0 / month

Who it's for: First-time users, occasional personal use.
What you get: Claude in chat, a limited number of messages per day, access to the current model, basic projects.
How the limits feel: With intensive use, you'll hit the daily limit after 1–2 hours.

Pro — approx. €20 / month

Who it's for: Anyone who uses Claude regularly (several times a week).
What you get: ~5× more messages than Free, unlimited projects, extended knowledge base (RAG), longer conversations.
How the limits feel: Sufficient for most personal users and occasional sales and recruiting tasks (without real candidate or client data).

Max — €100–200 / month

Who it's for: Power users who keep Claude open all day.
What you get: 5×–20× higher limits than Pro, priority during peak load.
How the limits feel: Practically none. Considerably oversized for normal everyday use.

Team / Enterprise

Who it's for: Solo entrepreneurs with sensitive data or teams (e.g. danic.ai) that work with customer and candidate data.
What you get: A data processing agreement (DPA), no training use of your data, user management, shared projects.
How the limits feel: The only path to GDPR-compliant use with actual client and candidate data.

My suggestion — pragmatic:

Free for 2 weeks. Then upgrade to Pro once you notice you're using Claude regularly. Only switch to Team before you concretely plan to use Claude with identifiable client or candidate data — and even then only after consulting a data protection officer or lawyer.