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.
"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.
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 chapterWeek 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 ProjectsMonth 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 promptsBe 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
2. A tough reply to a critical LinkedIn comment
3. Plan a solo city trip — in one go
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.
The six areas of Claude
That's all you need to understand. Each area has a clear purpose — and its own page in this guide.
Chat
The main window. One question, one answer. Like a conversation with a smart colleague.
Projects
A dedicated "room" for a recurring topic (e.g. danic sales outreach). Claude remembers guidelines and files.
System Prompts
A kind of "job description" for Claude. Permanently defines style, role, rules, tone.
Artifacts
When Claude builds a "real" document, a form, a spreadsheet, or a small application instead of just answering.
Sales Use Cases
Ready-made scenarios for the three income streams: danic.ai sales, executive search, precious metals content.
Building Use Cases
Content production, weekly planning, taxes, travel, fitness, personal letters — making the invisible tasks more efficient.
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.
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).
"'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").
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
Model (Sonnet, Opus, Haiku)
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
Hallucination
System Prompt
Project
Artifact
Connector / MCP
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?".
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.
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
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.
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."
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."
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."
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'."
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."
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."
7. Revive a language
"I learned Spanish at university. I want to reactivate it on the side, without an app — 10 minutes a day."
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."
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."
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."
Common beginner mistakes and how to fix them
"The output was nonsense." → You gave too little context
"It was too long." → Set a word limit
"It sounds like AI." → Say what it should not sound like
"The facts were wrong." → For current facts, enable web search or prompt differently
"It assumed too much." → Stop it and ask 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:
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.
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.
"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.
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.
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.
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".
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.
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.
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.
🎯 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)
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
📚 Professional Development & Literature Overview
Summarize studies, understand guidelines, compress new recommendations into two paragraphs. Here, Claude becomes your personal, critical editor.
Project Instructions (copy)
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"
📣 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)
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
🪙 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)
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)
🏠 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)
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
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.
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.
"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.
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.
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.
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:
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.
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.
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.
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.
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.
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.
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.
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.
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.
Solo Travel Planner
For solo city trips, weekend getaways, workation setups, travel logistics.
Letters to Authorities & Insurers
Matter-of-fact, precise letters — polite but firm. Never threatening, never submissive.
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."
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.
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.
"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."
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.
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.
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."
Just write: "Make this a document." or "Create this as a downloadable Artifact." Claude understands that.
Five types of Artifacts that matter to you.
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.
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.
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.
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.
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.
Artifact prompts you can take with you right now.
Copy, paste, adapt. All prompts reliably trigger an Artifact because they are structured enough.
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.
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.
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.
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.
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.
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.
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.
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.
Working with Artifacts — editing, sharing, saving.
-
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.
-
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.
-
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.
-
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.
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.
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.
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.
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.
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.
"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."
- Prepare a danic.ai discovery call
- Cold outreach: LinkedIn message to a CTO / VP Engineering
- Prepare a pilot proposal — after the discovery call
- Objection handling — the cheat sheet
- Follow-up after silence — polite but firm
- LinkedIn personal-brand post on agentic coding
- Quarterly pipeline review for yourself
- Executive search: build a long list for a C-level position
- Executive search: cold outreach to passive C-level candidates
- Executive search: reference check guide
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Weekly, the numbers are too small for signal. Monthly gives enough volume for patterns to become visible — without you drowning in data.
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.
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.
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.
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.
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.
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.
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.
"Sunday is my planning and content day. Cutting precious metals reels, weekly plan, travel planning, that one letter to the tax advisor. What used to take three hours is now 45 minutes. The rest of the time I go outside."
- Precious metals content plan for one month
- YouTube video script: 8 minutes of depth
- Preparing a sales conversation — initial precious metals consultation
- Precious metals FAQ as an evergreen sales asset
- Weekly planning with three income streams
- Letter to your tax advisor with multiple income sources
- Planning a solo city trip — compact, without family
- Car sale listing for mobile.de
- Letter to your landlord or a government office
- Weekly fitness plan: strength training + cardio + recovery
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.
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.
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.
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.
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.
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."
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.
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").
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.
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.
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.
My standard: placeholders like [AMOUNT] / [DATE] / [TAX ID]. I add the real numbers to the finished letter myself. Never through the LLM API.
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.
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.
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.
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.
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.
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.
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.
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.
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.
"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."
- Which Claude plan is suited for what?
- What happens to my inputs?
- What you must never enter
- Anonymizing — the practical guide
- Understanding hallucinations
- Your responsibility remains
- EU AI Act — what applies to recruiting from August 2026
- Pre-use checklist before every use
- When the data protection officer needs to be involved
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.
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.
What happens to your inputs?
-
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.
-
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.
-
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.
-
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.
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.
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
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.
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
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.
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.
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.
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.
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.
- 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
-
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.
-
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.
-
Specific numbers without context
"The ROI rate is 73%" — where does that number come from? From which study, which market, which sample? Ask.
-
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.
— "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'."
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.
You get many things faster and better. But proofreading, checking, signing off — that is on you. Always.
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.
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).
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.
-
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.
-
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.
-
Have I disabled training?
Settings → Privacy → "Help improve Claude" → off. Check it once, and you're done.
-
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.
-
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 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
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.
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.
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.
"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."
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.
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.
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.
There are a few more icons — for projects, artifacts, models. They come later. Today you'll only use the text input field. Really.
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
Test 2 — Draft an email
Test 3 — Something personal: restaurant suggestions
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.
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.
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.
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.
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.
You're in. What now?
You've done the most important part. Three paths, depending on what feels closest right now:
Understand the chat window
How to write really good prompts — the anatomy of a helpful prompt in 4 steps.
To the chat chapterUse Cases in Sales
10 concrete scenarios — danic cold outreach, discovery preparation, pilot memo, objection handling, exec search — as ready-made templates.
Sales Use CasesUse Cases in Building
Precious metals content, YouTube scripts, weekly planning, the tax advisor letter, travel, fitness — making the invisible work more efficient.
Building Use Cases