Use Claude with confidence — in the practice and at home.
No tech knowledge required. No generic AI phrases. This guide shows you visually, in the right order and with more than 60 ready-to-use prompts, how to put Claude to work on real everyday medical problems from day one — from patient communication to vacation planning.
"I have never used ChatGPT or Claude. But my daughter says it changes everything. I want to understand where it helps in the practice and in my personal life — without a degree in prompt engineering."
Dr. Brehm accompanies you through every section of this guide. Every example comes from her real practice or family life.
Three clear stages — no overwhelm
This is how you build confidence step by step, without having to deal with every feature at once on day 1.
Day 1 — First wins
Create an account, understand the chat window, complete three simple tasks (patient education text, email, research). Pure experimentation.
Go to the starter chapterWeek 1 — Projects and routines
Set up your own "rooms" for practice and personal life (Projects). Store templates and your own writing style once — Claude remembers.
Discover ProjectsMonth 1 — Your own assistants
Write system prompts, shape your own "staff members" — e.g. a patient-letter assistant, a travel planner, a literature scout.
Build system promptsBe impressed in 5 minutes
Three prompts that show the difference immediately. Just copy, paste into Claude, read the answer.
1. Patient education text for a patient in plain language
2. A difficult reply to a review on Google Maps
3. Plan a family trip — in one go
You do not 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 forget. Claude takes care of the rest.
The six areas of Claude
You do not need to understand more than this. 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. practice marketing). 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 replying.
Practice applications
Ready-made scenarios for the dental practice: communication, research, administration, continuing education.
Personal applications
Family, travel, finances, hobbies, learning — make the invisible tasks of everyday life more efficient.
Never enter real, identifiable patient data into Claude. Not the full name, not the date of birth, not the insurance number. That is non-negotiable — and it is not 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 time, 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, does not "practice" a profession and remembers nothing you told them yesterday (unless you tell them 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 bright 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 been a patient themselves, has never run a practice, is not licensed to practice — and their library is frozen at a certain 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 have set up a permanent desk for them (that's "Projects" and "Memory").
Claude is ideal for everything you read, check, and cross-verify yourself with clinical experience. He is not suited to being the sole medical decision-making authority. You remain the doctor — Claude is the fast, friendly staff member.
What Claude can do — and what it can't
Claude is very good at…
- Drafting texts (patient letter, email, blog article, patient-education text)
- Simplifying complex content — to any desired language level
- Structuring (lists, comparison tables, SOAP notes, pros/cons)
- Translating between languages — including medical texts
- Summarizing long documents (guidelines, PDFs, studies)
- Brainstorming and collecting differential-diagnosis ideas
- Building code, spreadsheets, small web apps, and visualizations
- Describing and interpreting images (e.g. an ECG sketch, a photo of findings)
Claude is poor or dangerous at…
- Independent clinical decisions (never without your review)
- "Current" information without an active web search
- Guarantees — hallucinations do occur, always cross-check
- Real patient data — never enter anything identifiable
- Legally binding statements without medical / legal 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 at a high level?
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 refer back to everything that came before.
Claude responds — and you iterate
The first answer is rarely perfect right away. 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, connection to Google Drive, calendar, Notion, and others (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 doctors, 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 dental practice and in private life, Claude's default setting is the right one. You don't need to change anything. For those who want the details:
Sonnet
The fast all-rounder. Ideal for emails, patient-education texts, research, brainstorming, daily planning. Default in Claude Pro.
Opus
The strongest model. Worth it for long, complex tasks — e.g. when you want a 60-page guideline summarized or a complex cover letter drafted.
Haiku
The fastest, lightest model. For very short, quick queries — such as "What's that medication called again with active ingredient X?".
Just leave it on the default setting. Switch only when you notice that a task really needs long answers or particularly difficult reasoning — then use Opus.
The chat — your always-available 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, refine. Here you'll learn what separates a good prompt from a bad one — and collect ten templates that fit straight into your daily routine.
When is the chat the right tool?
The chat is right for…
- One-off, quick requests
- Quick research and "what if" questions
- Spontaneous patient communication
- Ad-hoc translations or explanations
- Summaries of long texts
- Brainstorming and differential-diagnosis ideas
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 have to be re-briefed 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), what to watch out for (constraints). You don't have to phrase them in this order — but the more of them your prompt contains, the better the answer.
Bad → better → very good: the same task in three stages
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-made prompts — straight from Dr. Brehm's daily routine
You can copy each of these prompts as-is, adapt it to your situation, and paste it into Claude.
1. Explaining findings in plain language
"Ms. M. took her lab results home but doesn't dare to ask. I want to explain to her in one sentence that her thyroid values are borderline."
2. Getting a quick overview of a current guideline
"I don't have the DGZMK/DG PARO guideline on periodontitis therapy at hand and need the key points for a conversation in 20 minutes."
3. An empathetic rejection for a dental sales rep
"I received three appointment requests from dental sales reps today. I want to decline all three politely but firmly."
4. Differential diagnosis brainstorming
"I have an unclear case — a 38-year-old patient with recurring pressure pain in the right posterior maxilla, clinically no obvious caries. I want to be sure I'm not missing an avenue."
5. Birthday speech for the father-in-law
"My father-in-law is turning 75. I have to give a short speech — and can't find a way to start."
6. Preparing 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. Reviving a language
"I learned Spanish at university. I'd like to reactivate it on the side, without an app — 10 minutes a day."
8. Writing a dental assistant job posting
"I need a new dental assistant and can't find one. Maybe it's partly my old ad."
9. Talking through a parenting question
"My daughter (13) wants a smartphone. I'm unsure. I need clarity before we talk about it."
10. Summarizing a guideline PDF
"I downloaded a 60-page DGZMK guideline. I need it as a 5-minute update."
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 medical 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 get extremely close to the goal. Example iteration:
It's not "the perfect prompt". It's the willingness to iterate in 3–4 steps. Once you internalize that, you have 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.
"Every single time, I write to Claude all over again: 'Answer in my practice's style, keep it short, casual with patients, always include a note to check back with us, no jargon.' By the tenth time, it gets annoying. There has to be a way to store this once."
There is. It's called a Project.
Chat vs. Project — the decisive difference.
Project
- For recurring topics ("Patient communication")
- Its own instructions, stored once
- Its own files (e.g. practice guidelines) — Claude always has them "on the table"
- All chats inside it share the same guidelines
- You open the Project — and start working immediately
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 things, bad for recurring ones
Important: within a Project, you still have as many individual chats as you like. The Project is not "one single, everlasting 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 tell Claude permanently how to behave in this Project: role, tone, language, length, formats, taboos. This is not a one-off prompt — Claude automatically reads these instructions in every chat in the Project. A good project-instructions text is 100–400 words long.
Knowledge base ("library")
Files that Claude has "on the table" in every chat of the Project: your practice guidelines, your own style guide, FAQs, templates, patient-education 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 visibly saved. You can jump back at any time. Different chats do not share memories, though — each chat starts "fresh" with the background knowledge from building blocks 1 and 2.
Project instructions are a special kind of "system prompt", just project-specific. 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'm working on X".
Create a Project — in 4 clicks.
Left sidebar → "Projects"
In the left column, click the menu item Projects (or
go directly to claude.ai/projects). You will see either an empty
overview (normal at the beginning) or your existing projects.
Top right → "+ New Project"
Enter a name ("Patient communication dental practice") and, optionally, a description. Both are visible only to you and have no influence on Claude.
Enter the project instructions
On the Project's main page, you will see an input field labeled "Instructions" or "Set custom instructions". This is where the text goes that we have 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 an area called "Project knowledge". Use the + symbol 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 physicians
Each template consists of a name, project instructions (to copy), and a suggestion for which files belong in the knowledge base.
🩺 Patient communication dental practice
For all patient-education texts, patient information, reply emails, and explanatory letters. Claude speaks here the way you would write — if you had unlimited time.
Project Instructions (copy)
Knowledge base — what to upload?
- Your existing patient-education texts (as style models — anonymize them first)
- A list of "forbidden terms" you never want to see in patient correspondence
- Optional: a file with frequent patient questions and your standard answers
📚 Continuing education & literature overview
Summarizing studies, understanding guidelines, compressing new recommendations into two paragraphs. Here, Claude becomes your personal, critical editor.
Project Instructions (copy)
Knowledge base — what to upload?
- PDFs of current guidelines (DGZMK, AWMF) — where publicly available
- A list of your indication focus areas ("Cardiovascular risk", "Peri-implantitis", "Endodontics")
- Your own notes from past continuing-education courses as "vocabulary"
📣 Practice outward communication
Website, Google profile, newsletter, answering-machine scripts, job ads, notices — you want to come across as a modern, attentive practice, not like 1998.
Project Instructions (copy)
Knowledge base — what to upload?
- Your current website as a PDF or screenshots
- A list of practice services, office hours, team
- Examples of texts from other practices that you like (URL as a note)
- A short "brand DNA" (10–15 keywords: "time, listening, honest, Berlin, dentist, local, no esoteric nonsense…")
🌍 Family life & travel
Vacation planning, weekend activities, birthday planning, family calendar, school communication. The Project space where you are not a physician, but a father or partner.
Project Instructions (copy)
Knowledge base — what to upload?
- A list of the year's most important family dates (school vacations, birthdays, holidays)
- A short note with favorite places ("We love South Tyrol, the Baltic Sea, the Black Forest, Italy…")
- The family's allergies / intolerances
- A few sample photos of daily plans that worked well in the past
🏠 Authorities, insurers, contracts
Letters to the health insurer, tax advisor, insurance company. Understanding contracts. Responding to outrageous demands in a factual but firm way. The area that drains energy every Sunday evening.
Project Instructions (copy)
Knowledge base — what to upload?
- Your current letterhead / address
- A list of the file 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. "Practice communication" and "Family" do not belong in the same Project, otherwise tone and style blur together.
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 are often more effective than rules
"Never use jargon without a translation", "Never longer than 200 words" — negative rules like these often work better with Claude than positive requirements.
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 patient data
Not even in the knowledge base. Create example files with fictional people. Details in the data protection 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 there to be only answers of the first kind."
That is exactly what system prompts are made for.
Three types of instructions — and why that matters.
Profile settings
Apply everywhere. Here you tell Claude who you are and how you work — regardless of the topic. Example: "Write concisely, avoid filler phrases, I am a physician".
Project Instructions
Apply only within one Project. Here you tell Claude how to behave for a specific topic — e.g. "patient 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. This 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, well-working template:
Do not put project-specific things in your profile settings, such as "You are a marketing copywriter for my practice". Otherwise that also applies when you ask for restaurant recommendations — and Claude will respond in confusing ways. Project-specific content belongs in Project Instructions, not in the profile.
Seven building blocks every good system prompt is made of
You do not 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 patient education texts in a dental practice." Avoid roles that are too generic ("You are a helpful assistant" does not help Claude).
Audience / context
Who is Claude actually writing or thinking for? "The recipients are patients 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 cliches". Better 5 specific rules than 20 vague ones.
Content rules (dos)
What Claude should always do in terms of content. "Every text ends with a clear next step for the patient." "For medical recommendations, always add 'if in doubt, please contact the practice first'."
Content taboos (don'ts)
Often more important than the dos. "Never give specific dosages without my explicit instruction." "Never make diagnoses." "No promises of cures." "Never use jargon without a translation."
Format standards
Length, structure, language. "Standard length: 120–180 words, unless I explicitly request otherwise. Letters: salutation, body, closing 'Kind regards, your practice team Dr. Brehm'."
Self-check before every answer
A small "pre-flight checklist" Claude mentally runs through before every answer. "Have I made a claim I cannot substantiate from the source?", "Have I used jargon without a translation?", "Does the text end with a next step for the patient?" — Three questions like these noticeably improve quality.
Claude writes your system prompt — for you.
You do not 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 — simply paste it into a normal chat — delivers a tailor-made 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 is not perfect, simply say: "Tighten point 3, it's too soft for me. Add a point about X." Iteration is part of the method.
Six ready-to-use system prompts
Each one is ready to use immediately. Copy it, drop it into your profile or a Project, adjust it lightly in one spot — done.
Patient education text assistant
For all patient information, leaflets, procedure consent information, and written explanations.
Referral letter drafting assistant (fully anonymized)
Important: this prompt works exclusively with fictional or anonymized cases. Real patient data does not belong in Claude (except Claude for Work with a data processing agreement). Read the data protection chapter.
Literature & guideline summarizer
For weekend continuing education. You provide a study or guideline as a PDF / text / link, and Claude delivers the dentally relevant summary in half a page.
Practice marketing copywriter
Website, Google profile, notices, job postings, answering machine scripts. HWG-aware, without marketing cliches.
Family travel planner
For planning family vacations, weekend trips, travel logistics.
Letters to authorities & insurers
Factual, 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 did not fit. After 5 such moments you have 5 new rules for your system prompt.
2. Prohibitions often work better than instructions
"Never hedge with the conditional" 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, further editable. Those are Artifacts. They change how you work with Claude.
"I asked Claude to create a checklist for the U9 preventive checkup. Suddenly a separate document appears to the right of the chat — formatted, with checkboxes, 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 with 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 on the pros and cons of a therapy. You read, reply, move on.
Artifact
A 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, the 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 patient letter."
Structure
You ask for a clearly structured document — checklist, table, letter, report. Example: "Create a checklist for the hygiene training."
Reuse
You want to reuse the result later, copy it, or save it as a file. Example: "Make a template for the informed-consent form."
Visualization
You want a diagram, a table, or a process plan. Example: "Show me the treatment workflow as a flowchart."
Simply write: "Make this as a document." or "Create this as a downloadable Artifact." Claude understands that.
Five kinds of Artifacts that are relevant for you.
Letters, reports, patient education texts
This is the most common type. Cleanly formatted with headings, paragraphs, lists. You can download it as Word or Markdown, copy it, reuse it.
Structured lists, comparisons
When you compare or list something — drug interactions, treatment options, differential diagnosis — a table is often the result. Readable, copyable into Excel.
Flowcharts, process plans
"Show me the workflow of the U9 checkup as a diagram" — Claude builds a visual schema that you can print out or embed in a presentation.
Calculators, quizzes, interactive aids
Claude can also build simple interactive tools — for example a BMI calculator for the practice website or a small symptom self-assessment tool. Usable directly in the browser.
Simple HTML pages, templates
For your own practice website or a letter with letterhead — Claude can output a finished HTML page. You see the page rendered on the right, can test it and download it. That is the pro level; for starters, text Artifacts are entirely sufficient.
Artifact prompts to take with you right away.
Copy, paste, adapt. All prompts reliably trigger an Artifact because they are structured enough.
1 — Patient info sheet for diagnosis XY
A one-page info sheet you can hand to patients with a new diagnosis. Understandable, reassuring, without technical jargon.
Claude can write something wrong or imprecise even on the classics. You remain responsible for the medical content.
2 — SOP checklist for the practice
A reusable checklist — for example for the monthly hygiene training, the emergency equipment, or restocking the treatment rooms.
3 — Treatment pathway as a flowchart
A visual workflow — great for patient communication, dental assistant training, or as a poster in the waiting room.
4 — Packing list for the family vacation
A complete packing list sorted by person — created once as an Artifact, adapted once, and it's set for the next ten vacations.
5 — Weekly menu planner as a table
Seven days, three meals, with a shopping list at the end — exactly what is annoying on Sunday evenings.
6 — Small BMI calculator for the practice website
A simple, interactive tool that you can embed on your practice website. Patients enter height and weight and see the result immediately.
Claude writes the code. You see the finished tool directly in the Artifact window, can try it out and download it. Your webmaster or practice service provider gets the file and embeds it.
Working with Artifacts — edit, share, save.
-
Improve iteratively
Just say: "Make the 'Aftercare' section longer." or "Remove the medical 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 copy the entire text to the clipboard with one click and paste it into your practice management system.
-
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 patient-related content.
-
Reference it in the chat
You can keep referring to the Artifact in the ongoing conversation: "Write a shorter version of the patient letter for our email reply." Claude knows which document you mean.
Three pitfalls you should know about.
How it works well
- Say clearly what should be in the document — outline, length, target audience.
- Have changes made iteratively ("rewrite only section 2").
- Read everything through before sending.
- Anonymize patient data before entering it.
How it goes wrong
- Forwarding the Artifact to the patient inbox without reviewing it.
- Trusting "that's probably right" on medical content.
- Passing on Artifact links carelessly (they are public!).
- Using real patient names in the prompt.
Everything you write into the prompt — even if the result ends up in the Artifact — is sent to Anthropic's servers. Patient data does not belong there. For details, see Data Protection & Limits.
From here on it gets concrete: on the next pages you will see ten professional and ten personal use cases — each with a ready-to-use prompt.
Ten use cases for the practice.
From patient education texts to letters to authorities — ten tasks that come up in every dental practice, each with a copyable prompt. Skim through, pick out what you need today.
1. No real patient names, addresses, dates of birth, insurance IDs, or findings in the prompt. 2. Have every text professionally reviewed before sending — Claude can be factually wrong. 3. No medical data in the Free/Pro/Max plan. Details: Data Protection & Limits.
"I used to spend another two hours writing letters after the practice closed. Now I write a prompt, read the reply, change two sentences. Ten minutes. The rest of the evening, I see my kids."
- Rewrite a patient education text in patient-friendly language
- Answer a patient email politely and clearly
- Politely decline a dental sales rep inquiry
- Summarize a clinical guideline on one page
- Condense a study/article for everyday practice
- Texts for the practice website
- Write a job ad for a dental assistant
- Answering machine scripts for the practice
- Structure continuing education notes
- Letter to authorities (KZV, building authority, public health office)
1 — Rewrite a patient education text in patient-friendly language
The official patient education forms from the professional associations are legally bulletproof — but incomprehensible to many patients. Claude turns a technical text into a patient version that you include as a supplement.
"I can't spend twenty minutes explaining to every patient what a root canal treatment is. Now everyone gets a one-page comprehension sheet in addition to the formal informed-consent documentation — and the conversations get shorter and better."
The patient version does not replace the legally required original informed-consent form. It is a comprehension aid — and that should be clearly stated on the page as well.
2 — Answer a patient email politely and clearly
Patients often write long and emotional messages. You reply briefly and factually. Claude bridges that gap without sounding cold.
"I decide what the content is. Claude makes sure it doesn't sound like an official government notice."
3 — Politely decline a dental sales rep inquiry
Four inquiries per week. Answering each one individually costs time. With a Project and a System Prompt, it's a thirty-second job.
If this happens often — which it usually does — create a Project "External communication" with a System Prompt. Then all it takes in the chat is: "Decline dental sales rep." Claude knows the rest. See Projects.
4 — Summarize a clinical guideline on one page
An S3 guideline often runs 200 pages. You have ten minutes. Claude turns the full guideline into a practice-ready summary — which you then check against your own recollection of the original guideline.
Helpful, but no substitute for the original. For any specific patient case that depends on it: open the guideline itself and look up the relevant passage. Claude can misinterpret or omit details.
5 — Distill a study/article for daily practice
You have a study from Deutsches Ärzteblatt or the NEJM open. Forty pages. The question: Does this change how I practice on Monday?
6 — Copy for the practice website
Most practice websites read as if they were built in 2008 by the dental assistant's son. With one hour of Claude work, you get a complete body of copy for a professional practice site.
7 — Write a job posting for a dental assistant
Job postings that work don't sound like paperwork — they sound like a place where people want to work. Claude can do that, if you honestly describe what your practice stands for.
8 — Voicemail scripts for the practice
One script for regular office hours. One for vacation time. One for Wednesday midday. One for emergencies. All written cleanly once, clearly spoken, with no tongue-twister sentences.
9 — Structure continuing-education notes
Three days of conference, twenty-five lectures, a hundred handwritten notes. Claude turns them into something you will still understand in four weeks.
You can simply photograph your handwritten notes and upload the photo to Claude. Claude reads the handwriting, converts it to text, and structures it according to the format above. Works surprisingly well — as long as the handwriting isn't completely illegible.
10 — Letter to an authority (KZV, building authority, public health office)
A letter that sounds appropriately formal, is factually precise, and promises nothing you can't keep.
Bookmark this page. The first time you use each case, it may take ten minutes — by the third time, it's three. The time you gain is worth every learning curve.
Ten use cases for your personal life.
Trip planning, letters to the authorities, homework help, birthday poems, weekly meal plans. Ten everyday situations where Claude gives you two evenings a week back — each with a ready-to-use prompt.
"My wife asked me what I was doing on the laptop. I said, 'I'm planning the vacation.' She replied, 'You never plan the vacation.' Forty minutes later we had a complete itinerary for South Tyrol. Since then I've also planned the toy-themed birthday party. And the weekly meal plan."
- Plan a complete family vacation
- Weekly meal plan with shopping list
- Homework help for the kids
- Gift ideas for tricky occasions
- Write a birthday speech or poem
- Letter to your tax advisor or insurance company
- Write a car-for-sale listing
- Step-by-step DIY instructions
- Letter to the school / homeroom teacher
- Hobby research (wine, bikes, travel)
Here you can think more freely. But: even privately, never enter bank PINs, tax IDs, passwords, or your family's health data into Claude. That remains a hard line — see Data Protection & Boundaries.
1 — Plan a complete family vacation
From destination to daily itinerary. Claude delivers a complete draft that you then adjust to your preferences.
"I hate trip planning. My wife hates that I hate trip planning. Claude solved our marital problem."
Claude knows many places from its training data — but restaurants close, opening hours change. Before booking, verify briefly online or ask Claude to use web search (feature can be enabled in Claude.ai).
2 — Weekly meal plan with shopping list
Sunday evening, 7 p.m. The same old question: "What are we cooking next week?" Claude answers it in thirty seconds.
3 — Homework help for the kids
You're a dentist. Yes, your husband is a math teacher — but he's on a class trip today. Your nine-year-old son needs help with fractions. Claude explains it the way a good teacher would — patiently, age-appropriately, without doing the work for them.
If you sit next to your child and they type the answers themselves, they learn not just the material but also good habits with AI: ask follow-up questions, don't believe everything, try your own solution first.
4 — Gift ideas for tricky occasions
Your mother-in-law is turning 75. A colleague is retiring. An acquaintance's thirteen-year-old daughter has a birthday. Claude doesn't deliver generic ideas, but concrete suggestions — if you describe things concretely.
5 — Write a birthday speech or poem
Tomorrow you have to give the speech at your parents' golden wedding anniversary. Or write a poem for your daughter's birthday. Claude doesn't write for you — Claude delivers a good draft that you then bring into your voice yourself.
6 — Letter to your tax advisor or insurance company
You want to be clearly understood — without hours of back-and-forth by email.
No tax ID, no account balance, no insurance policy number. Keep it general — you fill in the letter with the actual numbers yourself before sending it.
7 — Write a car-for-sale listing
A listing that doesn't look like a "sloppy private sale" — but factual, trustworthy, complete.
8 — DIY Instructions Step by Step
Hanging a lamp. Hooking up the washing machine. Drilling into a concrete wall. Claude gives you careful, correct instructions — and tells you clearly when you should call a professional.
Claude knows the theory. But your old building, your specific wiring, your actual fuse-box situation are known only to you and an electrician. When in doubt: read the instructions, then make the call.
9 — Letter to the School or Homeroom Teacher
A sick note covering several days. A request for leave for a family occasion. A constructive reply to a school notice you don't agree with.
10 — Hobby Research (Wine, Bikes, Cars, Travel)
You've been reasonably serious about wine for two years now. But you don't want to become a sommelier — you want to know which Pinot Noir to bring to the next family dinner without embarrassing yourself.
If you describe honestly where you stand — beginner, intermediate, advanced — you won't get a textbook answer but a personal recommendation. Works for wine, bicycles, cameras, books, travel destinations, whisky, classical music, hiking routes.
Data protection, GDPR, and the limits of Claude.
This page is not optional. If you work with Claude in your practice, you are responsible — for the data, for the correctness, for the consequences. Here is what you need to know. Clear, without legal waffle, but precise.
Never enter patient data into the consumer versions of Claude. Free, Pro, and Max are not intended for anything patient-related — not even "just briefly", not even "just this one case". Period.
"I had the idea of having Claude type up a referral letter — after all, I had only entered the diagnosis and a few keywords, no name. My data protection officer called me before I could hit 'Send'. Patient data is not just name and date of birth. That was an important lesson."
- Which Claude plan is suitable for what?
- What happens to my inputs?
- What you must never enter
- Anonymizing — the practical guide
- Understanding hallucinations
- Your medical responsibility remains
- EU AI Act — what applies from August 2026
- Pre-use checklist before every use
- When to bring in the data protection officer
Which Claude plan is suitable for what?
Anthropic offers various plans with different contractual assurances. For use with patient 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 patient 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 patient reference. Practice texts, marketing, letters, research, 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) and additional security and compliance options.
Here too: The DPA alone does not automatically make use with patient data permissible. You also need your own data protection impact assessment (DPIA), your DPO's approval, and — sensibly — a restriction to clearly defined use cases.
Recommendation: If you want anything patient-related, 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 encrypted 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 servers' working memory.
-
Storage of the conversation (chat history)
Your chats are stored in your account so 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, the corresponding option is usually switched off by default. Check this in your account: Settings → Privacy → Help improve Claude. Turn it off deliberately — and document it in writing.
They are just not baked into future model versions. But they do 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 patient data
- Name, date of birth, address
- Insurance ID, statutory health insurance number
- Phone, email
- Photo, copy of ID
Medical findings with personal reference
- Original referral letters
- Lab results, imaging
- Medical history texts with identifiers
- Indirect identification too (rare + region + diagnosis)
Your own sensitive data
- Passwords, PINs
- Bank details, account statements
- Tax IDs, social security
- Confidential material from ongoing proceedings
Practice-internal confidentiality
- Personnel files of the dental assistants
- Salaries, contracts with identifiers
- Confidential correspondence
- Practice management system data
That's often not enough. A 47-year-old female patient from Berlin-Prenzlauer Berg with a rare diagnosis is identifiable — even without a name. GDPR-relevant is anything that can identify a "natural person", on its own or in combination. The rule of thumb: When in doubt, it is personal data.
Anonymizing — how to do it right.
For many tasks you don't need patient data at all. You need the structures. Here's how to phrase requests without making patients identifiable:
Not like this
- "Write a letter to Ms. Schmidt, born 12.4.1962, regarding her root canal treatment on tooth 36 last Tuesday…"
- "Explain this finding to me: Pat. K.M., 67 years old, peri-implantitis region 16, sinus floor elevation 2019…"
- "Here is the report from oral and maxillofacial surgery — can you translate it into understandable language for the patient?"
Better like this
- "Write a sample letter to a typical endodontics patient who has a follow-up appointment coming up — placeholders for salutation and date."
- "Explain the finding 'advanced peri-implantitis stage III' in general terms — what treatment options are common?"
- "Here is an anonymized sample report (markers like [DATE], [PATIENT], [CLINICIAN]) — please write a patient-friendly version using the same placeholders."
The three anonymization techniques
Placeholders
Copy the original text and replace anything that identifies a person with markers:
[NAME], [DOB], [ADDRESS].
The markers remain in the result — you only fill in the real data
manually at the very end.
Generalization
Instead of "patient K.M., 67 y/o, from Berlin-Prenzlauer Berg, with X," say "a 65-year-old patient with X." Specific identifiers out, clinical constellation in.
Hypothesizing
"Imagine the following case: …" — this turns a concrete case into a teaching example. The model responds to the example; your clinical reality stays out of it.
An informed-consent text is general. A practice letter template is general. A guideline summary is general. Patient data is almost never necessary — it only sneaks in because we are used to thinking in concrete terms.
Hallucinations — when Claude is convincingly wrong.
Claude is a language model. It generates plausible text based on statistical patterns in training data. It doesn't know anything in the human sense. That has one specific consequence: sometimes Claude invents facts. Very convincingly.
- Invented study citations ("Müller et al. 2021 showed…") — with author, journal, page number, all completely made up
- Incorrect dosage information — plausible, but outside the guideline
- Incorrect information about drug interactions
- Wrong guideline versions or outdated recommendations
- Invented ICD or OPS codes
- Incorrect billing codes (GOÄ/EBM)
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 cite it or act on it.
-
Answers to difficult questions that are too smooth
Complex medical questions often have no clear-cut answer. If Claude still sounds like "The recommendation is…": become skeptical.
-
Specific numbers without context
"The success rate is 73%" — where does that number come from? From which study, which patients, which endpoints? Ask follow-up questions.
-
Confidence is not an indicator of correctness
Claude phrases false statements just as assuredly as correct ones. You cannot infer correctness from the tone of the answer.
— "For medical statements, always indicate
the level of uncertainty: 'established' / 'likely' / 'unclear'."
— "If you are unsure about a source, say so openly instead of
guessing."
— "Never invent study citations or guideline references. Prefer
'I don't have a specific source for this'."
Your medical responsibility remains — in full.
Even if you use Claude for preparation, for research, for writing — the legal and professional responsibility for what reaches your patient stays with you. Always.
Malpractice liability
If a patient is harmed by an incorrect treatment recommendation, you are liable. Not Anthropic. Not the model. You cannot invoke the defense that the AI said so.
Professional confidentiality (Section 203 of the German Criminal Code)
If you give patient-related information to an AI system not covered by a contract, that can be a breach of medical professional confidentiality — a criminal offense, independent of the GDPR.
GDPR fines
A GDPR violation can result in fines of up to 20 million euros or 4% of annual revenue (typically much less for SMEs, but five to six figures is realistic). On top of that come possible damages claims from individual patients.
Professional-law consequences
The state medical associations can take action in cases of gross violations of the professional code and data protection — up to questions about your license to practice in extreme cases.
You'll get a lot done faster and better. But proofreading, verifying, signing off — that's your job. Always.
EU AI Act — what you need to know as of August 2026.
The EU AI regulation (EU AI Act) has been in force since August 2024 and is taking effect in stages. Most general obligations for user organizations apply from August 2, 2026.
Risk classes
The AI Act classifies AI systems into risk classes. AI in the medical field can range from "limited risk" to "high-risk" depending on how it is used. Language models that make or prepare diagnostic or treatment decisions tend to be high-risk.
Transparency obligations
Patients must be able to recognize when they are interacting with an AI. AI-generated texts that go to patients should be identifiable as such — the legal line here is still in flux.
Human in the loop
For medical decisions, "human oversight" is mandatory. An AI may not make a medical decision autonomously or prepare it alone — the physician must review, approve, and take responsibility.
Documentation
Practices that use AI substantially in patient-related processes will have documentation and evidence obligations. Which ones exactly and from what threshold — that is still being specified in detail in guidance from the supervisory authorities.
Much of it will be specified through implementing regulations and guidelines from the EU and the national supervisory authorities. Keep an eye on the topic — through your DPO, your medical association, your KV.
Ten-second checklist before every use of Claude.
Train yourself to mentally run through these five questions before every prompt. After two weeks it becomes automatic.
-
Does it contain anything that identifies a person?
A name, a date of birth, an address, a photo, an insurance ID, a rare diagnosis plus a region — anything that makes a specific person identifiable? If yes: STOP. Anonymize or don't enter it at all.
-
Am I on the right plan?
Patient-related content only in Claude for Work with a DPA and after DPO approval. General content can go in any plan — as long as it contains no personal data.
-
Have I turned off training?
Settings → Privacy → "Help improve Claude" → off. Check once, done.
-
Do I understand what Claude is going to answer?
If you cannot judge the topic professionally, you cannot judge the answer either. Then Claude is the wrong tool for that case.
-
Do I have a strategy for verifying the answer?
Comparison with a guideline? Cross-checking with colleagues? Your own expertise? If the answer could have patient-related consequences, a review must take place before you act.
When should you consult your data protection officer?
Always involve them when:
- You are setting up a Claude business plan (Team/Enterprise)
- You want to use Claude in a process in which patient data could occur
- You are updating your practice's record of processing activities (ROPA)
- You need a DPIA (data protection impact assessment)
- You are unsure whether a specific use is permissible
Usually not necessary when:
- You are working with Claude privately (vacation planning, a letter to your tax advisor)
- You are doing practice tasks without any personal data (marketing, job posting, answering machine script)
- You are doing general continuing education, with no reference to specific cases
Dental practices are often not required to appoint a DPO (that depends on staff count and data processing), but they still bear the responsibility themselves. In that case: get external advice before you use Claude in patient-related workflows. There are specialized data protection consultants for medical practices, often referred through the medical associations, the KV, or professional bodies.
If you internalize the pre-use checklist, work in the right plan, recognize hallucinations, and preserve your medical responsibility, you can use Claude safely and productively. Data protection is not an obstacle — it is a routine you will quickly internalize.
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 around.
"I've just poured 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, but in 90 seconds.
You do this once. After that, next time you just log in — exactly like on any other website.
Open claude.ai in your browser
Type that 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 "Continue with Google" — one click, done. Alternatively, go the classic route with an email address plus a password of your choosing.
Confirm your phone number
Claude asks for your mobile number once to prevent spam accounts. You'll receive a 6-digit code via SMS, enter it — and that's it. Your number is not used for anything else.
Enter your date of birth & name
A few required fields to confirm you're of age and for how you'd like to be addressed. For the name, your first name is enough — you're talking to Claude, not a registrar. You can change this name at any time later.
You're in.
You 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 be doing today. You can chat for several hours before you even hit a limit. Paying 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 inserts 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. A click on "New chat" starts a fresh conversation.
3. Your initials (top right)
This takes you to the settings: change your plan, profile details, data protection options. You'll 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 only use the text input field. Really.
Write your first prompt.
Let's make it a sprint. Three tasks that will deliver a genuine aha moment in the next 5 minutes. Simply copy each prompt, paste it into the input field, press Enter — and watch what happens.
Test 1 — Translate a patient question into plain language
Test 2 — Draft an email
Test 3 — Something personal: restaurant suggestions
You've just seen, across three areas — medical explanation, business communication, personal life — what Claude can do for you. Now let's configure a few settings so that all of this keeps working sensibly for you long term.
Three settings you set once today.
Click your initials at the top right, then Settings. Three tabs matter:
Profile settings → "What should Claude call you?"
Enter your first name and briefly what you do. Example: "Dentist with my own dental practice in Berlin. I use Claude for patient communication, research, and personal topics like family and travel." Claude will then tailor its answers to you more effectively.
Privacy → Training set to "Off"
In the Privacy tab you'll find the option that controls 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 is important. On Team and Enterprise it is 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 patient 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 patient data you need Claude for Work (Team/Enterprise) with a data processing agreement (DPA), or a different provider. Read the data protection 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
For whom: First-time users, occasional personal use.
What you get: Claude in the 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
For whom: Anyone who uses Claude regularly (several times a week).
What you get: ~5× more messages than Free, unlimited Projects,
an extended knowledge base (RAG), longer conversations.
How the limits feel: Sufficient for most personal users and occasional
practice tasks (without patient data).
Max — €100–200 / month
For whom: 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. Significantly oversized
for normal practice use.
Team / Enterprise
For whom: A practice with staff who work with patient data.
What you get: A data processing agreement (DPA), no
training use of your data, staff management, shared Projects.
How the limits feel: The only path to GDPR-compliant use with
actual practice data.
Free for 2 weeks. Then upgrade to Pro when you notice you're using Claude regularly. Only switch to Team before you concretely plan to use Claude with identifiable practice data — and even then only after consulting your data protection officer.
You're in. Now what?
You've done the most important part. Three paths, depending on what feels closest to you right now:
Understand the chat window
How to write truly good prompts — the anatomy of a helpful prompt in 4 steps.
To the chat chapterUse cases in the practice
10 concrete scenarios — referral letter, patient education, research, marketing — as ready-to-use templates.
Practice use casesPersonal use cases
Family, vacations, gifts, letters to government offices, hobbies — making the invisible work of everyday life more efficient.
Personal use cases