Medicine has always evolved through tools.

The stethoscope changed how physicians listened. Imaging changed how they saw. Electronic records changed how they documented and communicated. Each shift initially felt optional, even controversial. Over time, each became standard.

We are now in another transition. But this one is different.

Artificial intelligen…

Read more

Most physicians use AI like Google. There is a better way — and it takes one afternoon. I built it. Here is how it works — and what paid subscribers get to skip straight to.

Let me start with the thing nobody says: you cannot break anything. There is no wrong folder name, no wrong file, no configuration that locks you out or crashes something. The worst that happens is the system does not know who you are yet. That is fixable in five minutes.

I say this because I trained before computers existed, and I built this setup myself. If I can do it, so can you.

The setup has six steps. The first three are free. The last three — including the exact files I use and the one prompt that runs my entire workflow — are for paid subscribers.

Here is where we start.

First: Get the right app

Go to claude.com/download. Download the desktop app. Install it like any other program.

When it opens, look at the top of the screen. You will see three tabs: Chat, Cowork, and Code.

Click Cowork. That is where we are working.

If you have been using Claude in your browser, this is different. The browser version does not have Cowork. You need the desktop app.

Second: Make one folder with three folders inside it

On your computer — Desktop, Documents, wherever you keep things — create a new folder. Name it anything. I called mine “Claude Cowork.”

Inside that folder, make three more folders. Name them exactly: ABOUT ME, OUTPUTS, TEMPLATES.

That is the whole structure. You are done with this part.

Third: Understand what the three files do

Inside the ABOUT ME folder, you will put three short documents about yourself. The system reads them before every task — before you type a single word. That is what makes the output sound like you instead of like a press release written by someone who has never met you.

File one tells it who you are.

File two tells it what you never want to see.

File three tells it what you are working on right now.

Writing these files is the actual work of the setup. It takes about thirty minutes the first time. After that, you update them once a quarter.

What goes in them exactly — the structure, the language, the things that actually change the output — is what paid subscribers get below.

Below is everything you need to finish the setup in one sitting: the exact structure of all three files, word-for-word instructions for each one, the Global Instructions text ready to paste, and the first prompt I speak every morning to start my workflow.

If you have been thinking about upgrading, this is a good moment. The files alone will save you two hours of trial and error.

── For paid subscribers ──

Read more

Subscribe now

I write a medical study summary for ObGyn Intelligence roughly twice a week. The format is always the same: title line, 150-word summary, 150-word “What it means,” 150-word “My Take.” Seventh-grade readability. No jargon. Output as a Word document.

I used to type these instructions every time. Then I realized I was doing what I tell my residents never to do—repeating a task manually when a system could handle it. So I built a Skill. Now I say “Summ,” attach a PDF, and Claude produces the finished summary without a single additional instruction.

Every time.

Exactly right.

Skills, Cowork, and Scheduled Tasks are the features that let Claude work without you standing over it.

Here are 10 steps to set them up.

The 10 Steps

The rest of this post is for paid subscribers

Quick reminder on how to access Claude Cowork:

1. Go to claude.com/download. Download the app on your computer.

2. You must have a Pro account ($20/month). I pay for the $100/month plan.

3. Open the app. Click on the Cowork tab at the top between Chat & Code.

4. Select a folder from your computer. More about it right after this set up.

5. Make sure to always select “Opus 4.6” for complex tasks. It’s the smart model.

Step 1: Understand what a Skill is. A Skill is a set of detailed instructions that lives inside Claude and fires automatically when triggered. It is like a standing order in medicine. You do not re-write the insulin sliding scale every time—the standing order exists, the nurse follows it. A Skill works the same way. You define the task once, including the trigger, the format, the output, and the rules. Claude follows the standing order every time it is triggered.

Step 2: Identify your first Skill candidate. Think about the task you do most often with Claude. The one where you give the same instructions repeatedly. Summarizing articles. Drafting patient letters. Reviewing a study design. Writing social media posts about your practice. Whatever it is, if you have typed the same instructions more than twice, that task should be a Skill.

Step 3: Use Skill Creator to build it. You do not need to write code. Claude has a built-in Skill Creator that interviews you.

Open Cowork and type “Create a new skill.”

Claude will ask you questions:

What should this skill do? When should it trigger? What format should the output use? What rules should it follow? Answer the questions in plain language. Claude builds the Skill from your answers. It writes the instruction file for you.

Share

Step 4: Define your trigger word. Every Skill needs a trigger—a word or phrase that tells Claude to activate it. Make it short and specific. Mine is “Summ” for study summaries. Another is “NotesMeme” for creating quote graphics. Choose something you will not accidentally type in normal conversation. When Claude sees the trigger, it stops asking questions and starts executing.

Step 5: Write the negative triggers. This is the part that separates a good Skill from an annoying one. Negative triggers tell Claude when NOT to use the Skill. Without them, Claude may fire the Skill when you did not want it. If your Skill summarizes studies, tell it: “Do NOT use this skill when the user is asking a general question about a medical topic. Do NOT use when no PDF is attached.” Negative triggers prevent the Skill from hijacking conversations where it does not belong.

Step 6: Test the Skill with a real example. Attach a PDF or provide the input the Skill expects. Use the trigger word. Check the output. Is it the right length? The right format? The right tone? If not, go back and refine the Skill instructions. The first version is never perfect. The third version usually is.

Step 7: Open Cowork for multi-step tasks. Skills handle single, repeatable tasks. Cowork handles complex workflows. Cowork is Claude with access to a folder on your computer. It can read your files, create new documents, run calculations, and execute multi-step tasks without you guiding each step. If Skills are standing orders, Cowork is an attending running the service. You give the objective. It figures out the steps.

Step 8: Give Cowork a folder to work in. When you open Cowork, it asks you to select a folder on your computer. This is its workspace. Put the files you want it to work with in that folder—data sets, drafts, protocols, templates. Cowork reads them, processes them, and saves its output back to the same folder. You do not need to copy and paste anything in or out of the chat window. The work happens directly on your files.

Step 9: Set up a Scheduled Task. If you have a task that should run at the same time every day or week, Claude can schedule it. Open Cowork and say “Create a scheduled task.” Tell it what to do and when to do it. Example: every Monday morning, scan a specific folder for new PDFs and produce a summary document. As long as your computer is running, the task executes on schedule. You walk in and the work is already done.

Step 10: Build your second and third Skills. After your first Skill works, build another. And another. Each one removes a repetitive task from your workflow. I have Skills for study summaries, peer reviews, CDC data analysis, LinkedIn posts, and visual abstracts. Each one took about 15 minutes to build. Each one saves me 30 minutes or more every time it runs. After a month, the compound effect is substantial. You are not working harder. You are working once, and the system runs.

My Take

The difference between using Claude as a chat window and using it with Skills is the difference between dictating every order verbally and having a functioning EMR with order sets. Both get the job done. One of them scales.

I produce roughly eight times more content now than when I was still seeing patients. That is not because I work eight times harder. It is because the repetitive parts—formatting, structuring, finding the right template—are handled by Skills I built once and have not touched since. My time goes to the part that requires a physician: reading the study, forming the opinion, making the clinical judgment.

If you completed the steps from the previous post—the Project, the about-me file, the instructions—you already have a Claude that knows you. Now make it work for you. Build one Skill this week. You will build five more by the end of the month.

Every morning, the same ritual. You open Claude, type your question, and spend the first three messages explaining who you are, what you do, and what you need. You are an ObGyn. You want evidence-based answers. You do not want a disclaimer telling you to consult your physician. You are the physician.

Then you close the tab. Tomorrow, you do it again. Claude has no memory of you. It is like seeing a new locum every shift who has never read a single chart.

It does not have to work this way. Claude has features that remember you, your files, and your preferences across every conversation. Here are 10 steps to set them up. Total time: about 30 minutes. You will never re-explain yourself again.

The 10 Steps

Step 1: Open a Project. In Claude, click “Projects” in the left sidebar and create a new one. Give it a name that describes its purpose. Mine is called “CDC Natality Analysis.” Another is “ObGyn Intelligence Writing.” A project is a workspace. Everything inside it—files, instructions, conversations—stays together and carries forward. Think of it as a dedicated chart for a specific type of work.

Step 2: Write your Project instructions. Every project has a text box at the top for instructions. This is where you tell Claude how to behave inside this project. Be specific. Mine says things like: “Always use Vancouver citation format. Write at 7th-grade readability. Never fabricate references. When I say Summ, produce a 400-word summary in three sections.” These instructions apply to every conversation you start inside this project. Write them once. They persist.

Step 3: Upload your key files. Drag your most-used documents into the project. Practice protocols. Your favorite review articles. Patient education handouts. Clinical guidelines you reference often. Claude reads these files before answering your questions. If your gestational diabetes protocol is in the project, you can ask “What does my protocol say about insulin initiation?” and Claude will answer from your document, not from a generic training set.

Step 4: Create your about-me file. Open any text editor. Create a file called about-me.md. Write a short description of yourself: your specialty, your clinical focus, your research interests, your communication preferences. Mine says I am an MFM specialist and ethics consultant, that I use CDC natality data, that I write for a general audience at obmd.com, and that I do not tolerate hedging language. Upload this file to your project. Claude now knows who it is working with.

Subscribe now

Step 5: Be specific about what you do not want. This is the part most people skip, and it matters more than what you do want. Tell Claude what to avoid. “Do not add disclaimers about consulting a healthcare provider. Do not use the phrase ‘more research is needed.’ Do not soften conclusions when the evidence is clear.” Negative instructions are more powerful than positive ones. They prevent the generic AI voice from creeping back in.

Step 6: Start a conversation inside the project. Open your project and start a new chat. Ask a question you have asked before in basic chat. Notice the difference. Claude already knows your specialty, your preferences, and your files. It skips the preamble. It writes the way you told it to write. The answer is not generic—it is shaped by your context. This is the moment most physicians realize what they have been missing.

Step 7: Test it with a real task. Upload a study you recently read. Ask Claude to summarize it for a clinical audience. Or ask it to draft a patient counseling script based on your uploaded protocol. Or ask it to compare two approaches using the guidelines you provided. The more you test it with real work, the faster you learn what instructions to refine.

Share

Step 8: Refine your instructions after the first week. After five or six conversations, you will notice patterns. Claude does something you did not want. Or it misses a preference. Go back to your project instructions and edit them. This is not a one-time setup—it is a living document. I update my instructions roughly once a week. The AI gets sharper each time because you get more specific each time.

Step 9: Create a second project for a different purpose. Once you see the value, create another project for a different part of your work. One for research. One for patient education. One for administrative tasks. Each project has its own instructions, its own files, its own memory. They do not bleed into each other. Your research project can be precise and technical. Your patient education project can be warm and simplified. Same AI, different context.

Step 10: Set Global Instructions for things that apply everywhere. Claude also has a setting called Global Instructions—sometimes called “Custom Instructions” in Settings. These apply across all conversations and all projects. Use this for universal preferences: your name, your credentials, your department affiliation, your default citation format. Project instructions handle the specific. Global instructions handle the constant. Together, they mean Claude never starts from zero again.

My Take

I spent 50 years building clinical knowledge. The idea that I should re-explain my expertise to an AI every single session is absurd. These features exist to solve that problem. They are not advanced. They are not technical. They are a text box and a file upload. If you can write admission orders, you can configure a Claude project.

The physicians who tell me AI is not useful are almost always the ones using basic chat with no context, no files, and no instructions. That is not AI failing. That is a misconfigured tool. Fix the configuration. The results follow.

Part 2 of the series “You Are Using 5% of Your AI.” Next: The Features That Work Without You.

Subscribe to ObGyn Intelligence at obmd.com

Last Tuesday, I asked Claude to check my Google Calendar for open slots, draft an email to a colleague about a manuscript revision, and save the draft to Gmail. Claude did all three without me switching a single application. I stayed in one window. Claude moved between the tools.

That used to require opening three apps, copying information between them, and remembering to follow up. Now it requires one sentence.

This is what happens when Claude connects to the tools you already use. It stops being a separate application you visit and becomes the layer that runs across everything. Here are 10 steps to get there.

The 10 Steps

Step 1: Understand what Connectors are. Connectors are bridges between Claude and the applications you already use—Gmail, Google Calendar, Slack, Google Drive, and others. When a Connector is active, Claude can read from and act inside that application. It is not a separate login or a new platform. It is Claude reaching into your existing tools. Think of it as giving your research fellow access to your email and calendar instead of making her walk to your office every time she needs information.

Step 2: Connect Google Calendar first. Calendar is the easiest Connector to start with because the risk is low and the value is immediate. In Cowork, Claude will prompt you to connect your calendar when you ask about scheduling. Follow the authorization steps. Once connected, you can say “What is on my schedule Thursday afternoon?” or “Find me a free 30-minute slot this week” and Claude answers from your actual calendar—not a guess.

Step 3: Connect Gmail. Once Calendar works, connect Gmail. Now Claude can search your inbox, read specific emails, and draft replies. This is not Claude sending emails without your permission. It drafts them. You review. You send. But the drafting—finding the right thread, pulling relevant context, writing in your voice—that part is handled. For someone who writes 30 emails a day, this is not a novelty. It is a time savings you can measure.

Subscribe now

Step 4: Connect Google Drive. If your documents live in Google Drive, connecting it lets Claude search and read files stored there. You can say “Find the manuscript draft I worked on last week” and Claude locates it. Combined with your Skills, this means Claude can find a file, read it, and process it—all without you downloading anything or pasting text into a chat window.

Step 5: Set up Global Instructions. Global Instructions are preferences that apply across every conversation and every project. They are the constants in your workflow. Your name. Your degree. Your department. Your citation format. Your writing style. Set these once in Claude’s settings. They run forever, in every context. When Claude drafts an email, it signs with your correct credentials. When it writes a summary, it uses your preferred format. No reminders needed.

Step 6: Try Dispatch from your phone. Dispatch is Claude’s mobile feature. It lets you send instructions to Claude on your computer from your phone. You are at dinner and remember you need a summary of a paper sitting in your Cowork folder. Open Dispatch, type the instruction, and Claude executes it on your desktop. When you get home, the work is done. It is remote access to your AI workflow—not remote access to your computer, but to Claude running on it.

Step 7: Use Claude Computer for native desktop apps. Claude Computer is the feature that lets Claude see and interact with your Mac screen. It can click buttons, read what is displayed, scroll through documents, and navigate applications that do not have Connectors. If you need Claude to pull data from a desktop application that has no API—a hospital reporting dashboard, for instance, or a reference manager—Claude Computer is how it gets access. You grant permission for each application. Claude never acts on your screen without your approval.

Step 8: Combine Connectors with Skills. This is where the system becomes more than the sum of its parts. A Skill defines what Claude does. A Connector defines where it does it. Combine them: a Skill that summarizes a study and a Gmail Connector that drafts the summary to your co-author. A Skill that generates a patient handout and a Drive Connector that saves it to your shared clinical folder. A Skill that reviews your weekly schedule and a Calendar Connector that identifies conflicts. Each combination removes a manual step from your day.

Step 9: Build a Cowork Project for persistent memory. A Cowork Project is a workspace that persists between sessions. Your files stay. Your instructions stay. Your conversation history stays. Unlike regular Projects that reset context, a Cowork Project remembers what you worked on last time and picks up where you left off. Use this for ongoing work—a manuscript in progress, a research analysis that runs over weeks, a content calendar you update monthly. You do not restart. You continue.

Step 10: Audit your workflow and automate one more task each week. Now step back and look at your week. Where do you switch between applications? Where do you copy information from one place to another? Where do you do the same task on a schedule? Each of these is a candidate for a Connector, a Skill, or a Scheduled Task. You do not need to automate everything at once. One new automation per week. In two months, your workflow looks fundamentally different—not because you changed how you practice medicine, but because you stopped doing manually what a machine should handle.

My Take

I hear physicians say they do not have time to learn AI. This is exactly backward. You do not have time not to learn it. Every hour you spend configuring these tools saves you multiple hours every week for the rest of your career. The return on investment is not linear. It compounds.

The physicians who will thrive in the next decade are not the ones who know the most medicine. Medical knowledge is no longer scarce—Claude has access to more literature than any human can read in a lifetime. The physicians who will thrive are the ones who know how to use that knowledge efficiently. Who can direct an AI the way a senior attending directs a team: clearly, specifically, with the judgment that only experience provides.

You started this series using 5% of Claude. If you have followed all three posts, you are now using most of it. The chat window was the lobby. You have been given the keys to the building. Use them.

Part 4 of the series “You Are Using 5% of Your AI.” This is the final installment. Read the full series at obmd.com.

Subscribe to ObGyn Intelligence at obmd.com

A colleague asked me last month why she should pay for Claude when the free version works fine.

I asked her if she would practice obstetrics with only a stethoscope because the free version of a Doppler is her ears.

She laughed.

But she was serious, and so was I.

The free version of Claude is a demonstration. It lets you type questions and get answers. It uses a smaller, less capable model. It limits how many messages you can send per day. It does not give you access to Projects, Skills, Cowork, Connectors, or any of the features that turn Claude from a chatbot into a working system. Using free Claude and concluding that AI is not useful is like test-driving a car in a parking lot and deciding cars are slow.

This post walks you through getting the paid version, setting it up correctly from the start, and understanding why the investment makes sense. Ten steps. Twenty minutes. The beginning of a fundamentally different workflow.

The 10 Steps

Step 1: Understand what you are buying. Claude has three tiers. The free tier gives you limited access to a smaller model. Claude Pro costs $20 per month and gives you access to the most powerful model (Opus 4.6), extended thinking, Projects, file uploads, and significantly more usage. Claude Team costs $30 per user per month and adds collaboration features for groups. For a solo physician, Pro is what you want. Twenty dollars. That is less than one month of UpToDate, less than a single CME credit, and less than what most of us spend on coffee in a week. The comparison is not even close.

Step 2: Go to claude.ai and sign up. Open your browser. Go to claude.ai. Create an account with your email address. You will start on the free tier. That is fine. Use it for five minutes to see the basic interface. Then upgrade. Click on your profile icon, select “Upgrade to Pro,” and enter your payment information. The upgrade is instant. You immediately gain access to everything the free tier hides behind the wall.

Subscribe now

Step 3: Select the right model immediately. Once you are on Pro, the first thing you do is select the model. At the top of any new conversation, you will see a dropdown that lets you choose which version of Claude to use. Select Opus 4.6. It is the most capable model available. The default model (Sonnet) is faster but less thorough—fine for simple questions, but you are not paying $20 a month for simple questions. You are paying for the best reasoning available. Use it. Also turn on Extended Thinking in the same area. This tells Claude to reason step by step before answering. For anything clinical, analytical, or complex, the difference is substantial.

Step 4: Download the desktop app. Claude works in the browser, but the desktop app is better. Go to claude.ai/download and install it on your Mac or PC. The desktop app gives you access to Cowork—the feature that lets Claude read and create files directly on your computer. The browser version cannot do this. If you plan to use Claude for anything beyond typing questions into a chat window—and you should—the desktop app is where you want to be. It takes two minutes to install.

Step 5: Set your Global Instructions. Before you do anything else, go to Settings and find Global Instructions (sometimes called Custom Instructions). This is where you tell Claude who you are, once, for every future conversation. Write your name, your specialty, your credentials, your department. Add your preferences: “I am a board-certified ObGyn. Give me evidence-based answers without disclaimers about consulting a physician. Use Vancouver citation format. Be direct.” These instructions apply everywhere, in every conversation, from now on. You will never type them again.

Step 6: Create your first Project. Click “Projects” in the sidebar. Create a new project and name it after your most common use case. If you read studies regularly, call it “Literature Review.” If you write patient letters, call it “Patient Communication.” In the project instructions box, write specific directions for how Claude should behave in this workspace. Upload two or three files Claude should know about—a protocol, a guideline, a template you use often. This is the foundation. Every conversation inside this project will have this context automatically.

Step 7: Write your about-me file. Open any text editor on your computer. Create a file called about-me.md. Write a paragraph about yourself: what you do, what you care about, how you like information presented. It does not need to be long. Mine is about 200 words. It covers my specialty, my research focus, my writing platforms, and my communication preferences. Save it and upload it to your project. This single file transforms Claude from a generic AI into one that responds in a way shaped by your expertise and priorities. Every physician I have shown this to says the same thing: “Why did I not do this months ago?”

Step 8: Test it with real work. Do not test Claude with toy questions. Open your project and give it a real task. Upload a study you need to read. Ask it to summarize a guideline. Have it draft a letter you actually need to send. Compare the output to what you got from free Claude with no context. The difference is not subtle. Free Claude gives you a generic answer that could be for any physician. Configured Pro Claude gives you an answer that is for you, using your files, following your rules, in your preferred format. This is the moment the $20 makes sense.

Step 9: Understand what you are not getting with the free version. This is worth stating plainly. The free tier does not give you Opus 4.6—you are stuck with the less capable model. It limits your messages to roughly 10–20 per day before it throttles you or downgrades the model further. It does not support Projects with file uploads. It does not give you Cowork, Skills, Connectors, Scheduled Tasks, or Claude Computer. It does not support Extended Thinking. In practical terms, the free tier is a text box that forgets you. The paid tier is a configurable system that learns your preferences, reads your files, and works across your tools. These are not the same product. They share a name.

Step 10: Commit to one week. Use Claude Pro for one full week. Use it every day, for real tasks, inside your project, with your about-me file loaded. At the end of the week, add up the time it saved you. For most physicians, the answer is somewhere between two and five hours. That is $20 for two to five hours of your time back. Every week. For comparison, the average ObGyn’s hourly rate is well north of $100. If Claude saves you even one hour per week, the subscription pays for itself five times over. After the first week, you will not debate whether it is worth it. You will wonder why you waited.

My Take

Physicians pay for UpToDate without blinking. They pay for society memberships, MOC fees, CME courses, and journal subscriptions. They accept that professional tools cost money. Then they try the free version of an AI that is more powerful than all of those tools combined, get a mediocre result, and say AI is overhyped.

It is not overhyped. You are undertooled.

The free version of Claude is a brochure. The Pro version is the product. You would not evaluate a new ultrasound machine by looking at the brochure. You would turn it on, scan a patient, and judge the image quality. That is what Step 8 is for. Try the real thing with real work. Then decide.

Twenty dollars a month. The best investment in your practice you will make this year.

A doctor colleague told me last week she uses Claude every day. I asked her how. “I type a question and it gives me an answer.”

That is it.

That is how she uses it.

She is a board-certified ObGyn running a busy practice.

An MFM.

And she is using the most powerful AI tool available the same way she would use Google in 2005.

She is not alone. Roughly 95% of physicians who use AI stop at the chat window. They ask a question, get a response, close the tab, and next time start from zero. The AI forgets them. They forget the AI can do more. Both sides lose.

This post is a plain-language guide to what Claude can actually do, written for ObGyns who have used the basic chat but nothing else. No coding. No technical background. Just the features that matter, explained in the order you should learn them.

What You Already Know

Chat is the basic window. You type, Claude answers. Think of it as texting a very smart stranger who has never met you before and will forget you the moment you close the conversation. Every session starts fresh. No memory, no context, no relationship.

Extended Thinking is a setting that tells Claude to reason more carefully before answering. Instead of giving you the first plausible response, it works through the problem step by step. For anything clinical or analytical, turn it on. It takes a few extra seconds. The answers are meaningfully better.

Opus 4.6 is Claude’s most capable model. Always select it. The default model is faster but less thorough. You would not send your resident to handle a complicated delivery when your MFM specialist is available. Same principle.

Subscribe now

The Features That Remember You

This is where most physicians never go, and it is where the real value starts.

• Projects are workspaces where you upload files and write instructions that Claude remembers across every conversation in that project. I have a project for CDC natality data analysis. Every time I open it, Claude already knows my datasets, my variable definitions, and my analytical preferences. I do not re-explain anything. Think of Projects as hiring the same research assistant every day instead of training a new one each morning.

• Context Files are documents you drop into a project so Claude can draw on them. Your practice protocols. Your patient education handouts. Your favorite review articles. The more context you give, the less prompting you need. Claude reads them before it reads your question.

• About-me.md is a single file that tells Claude who you are, what you do, and how you think. Your specialty. Your clinical interests. Your preferred communication style. Your pet peeves. Write this once, and Claude stops giving you generic answers. It gives you answers shaped by your expertise and priorities. This one file changes everything.

  Share

The Features That Work Without You

• Skills are sets of detailed instructions that live inside Claude and fire automatically when triggered. I have skills for summarizing medical studies, writing peer reviews, analyzing CDC data, and drafting LinkedIn posts. When I say “Summ” and attach a PDF, Claude does not ask me what I want. It already knows: 400–500 words, three sections, 7th-grade readability, output as a Word document. Every time. Without being told twice.

• Skill Creator is Claude’s built-in tool that interviews you about a process and then generates the skill for you. You do not need to write code. You describe what you want, answer a few questions, and Claude builds the instructions. If you find yourself giving Claude the same directions more than twice, you need a skill.

• Cowork takes this further. It reads your files, creates documents, runs code, and executes multi-step tasks. Think of it as the difference between dictating a letter and handing someone your entire filing cabinet and saying “prepare the quarterly report.” Cowork can access a folder on your computer, work through the files, and produce deliverables. I use it daily.

• Scheduled Tasks let Claude run jobs automatically on a schedule. Set it once, and it runs without you. As long as your computer is on, the task executes at the time you specified.

The Features That Connect Everything

Connectors plug Claude directly into your existing tools. Slack, Google Calendar, Gmail. Claude does not just answer questions about your schedule—it reads your calendar, drafts emails, and acts inside the applications you already use.

Global Instructions are persistent instructions that apply across every conversation, not just within a single project. Set them once. They run forever. Mine tell Claude my department affiliation, my writing standards, and where to save files. I never repeat these instructions.

My Take

I have been writing about AI in medicine since before most professional societies acknowledged it existed. The technology is not the bottleneck. The bottleneck is physicians who open the basic chat, get a mediocre answer to a poorly framed question, and conclude that AI is overhyped.

It is not overhyped. It is underconfigured.

The difference between basic chat and a fully configured Claude is the difference between asking a random medical student a question in the hallway and working with a trained research fellow who knows your data, your preferences, and your standards. The fellow does not just answer—she anticipates. That is what a configured AI does.

You do not need to learn all of this at once. Start with one thing: create a Project, upload your most-used protocols, and write a short about-me file. Use it for a week. You will not go back to the basic chat.

The 95% of Claude you have not touched is where the actual value lives.

Content, Tools, and Authority

Your Brand as a Clinical Platform
Your brand is not simply a newsletter or a website. It is a clinical authority platform, where evidence-based content, practical tools, and informed perspective come together to serve both professional and patient audiences. Building such a platform requires consistency, intellectual discipline, and a clear understanding of what you uniquely contribute. AI can support the process, but it does not replace the thinking behind it.

Read more

Clinical guidelines change. ACOG updates practice bulletins. SMFM publishes new consult series. USPSTF revises screening recommendations. NICE issues new guidance that often anticipates where US guidelines are headed. Keeping current with all of this, across the breadth of general ObGyn and maternal-fetal medicine, while maintaining a clinical practice, is genuinely difficult.

Most clinicians handle this poorly. They learn about guideline changes through conference presentations, from colleagues who happen to mention it, or when they go looking for the guideline to answer a specific clinical question and discover it has been updated. This reactive approach to guideline awareness creates real risk: clinical practice that does not reflect current standards, consent discussions based on outdated recommendations, and patient education materials that have quietly become incorrect.

AI can help you build a more systematic approach. This course describes how.

Read more

Patient education is one of the most resource-intensive and most frequently neglected components of clinical care. The evidence for its value is strong: patients who understand their conditions, their options, and what to expect from treatment have better adherence, fewer unexpected calls and visits, and better outcomes. The barrier is time: creating high-quality, individualized patient education materials takes more time than most practices have.

A well-designed patient education content engine, built with Claude and organized into a repeatable workflow, can transform this from a reactive, ad hoc activity into a systematic practice that produces consistently high-quality materials at scale. This course describes how to build it.

Read more

Publishing a Substack newsletter consistently, while maintaining a full clinical schedule, a research program, and the rest of a demanding professional life, is genuinely hard. The bottleneck is almost never ideas. Clinicians who are active in their field have more things worth writing about than they have time to write. The bottleneck is the conversion…

Read more

Academic writing is one of the most demanding and least taught skills in clinical medicine. Clinicians are trained extensively in how to practice. They are trained almost not at all in how to write about it. The result is a literature full of papers that contain genuinely important clinical science buried under prose that is unnecessarily dense, poorly organized, and harder to read than it needs to be.

AI does not write manuscripts for you, and it should not. But it is genuinely useful at several specific stages of the manuscript process, from organizing your argument to editing for clarity to anticipating the reviewer criticisms that are likely to come. This course covers how to use it well at each stage, and what to avoid.

Read more

Literature reviews are among the most time-consuming tasks in academic medicine. A thorough review of a clinical topic for a manuscript introduction, a grand rounds presentation, or a guideline commentary can take days of searching, reading, and synthesizing. Most clinicians simply do not have days to spare, which means literature reviews are often less thorough than they should be, or they are delegated entirely to trainees whose clinical judgment for filtering relevance is still developing.

AI does not eliminate the need for literature review. But it can compress the most time-consuming parts of the process dramatically. This course describes a complete literature review workflow that uses Claude at every stage where AI adds genuine value, while keeping human clinical judgment in the places where it is irreplaceable.

Read more

The CDC natality database is one of the richest sources of population-level obstetric data in the world. It contains birth certificate data on virtually every delivery in the United States, with variables covering maternal demographics, prenatal care, labor and delivery management, and neonatal outcomes. For a clinician interested in population-level trends in obstetric practice, it is an extraordinary resource.

It is also, for most clinicians, completely inaccessible. The raw data files are enormous. The variable coding requires a technical manual to interpret. The analysis requires statistical software and programming knowledge that most clinicians do not have and did not train for.

AI is changing that. This course is about how to use Claude to engage meaningfully with natality data, from understanding what the database contains to interpreting analyses, without needing a biostatistics degree or a research team.

Read more

Prenatal education is one of the highest-leverage interventions in obstetric care. Patients who understand their pregnancy, their options, and what to watch for have better outcomes and better experiences. But producing individualized, accessible prenatal education at scale is a genuine challenge for practices of any size.

AI changes what is possible here. This course covers how to build interactive prenatal education tools that are personalized, accessible, evidence-based, and created at a fraction of the cost and time of traditional approaches.

Why static prenatal handouts are not enough

The standard prenatal education model is built around static handouts: printed or PDF documents that cover standard topics at a standard reading level for a standard patient. The problem is that your patients are not standard. They have different gestational ages, different risk factors, different literacy levels, different languages, different anxieties, and different prior pregnancy experiences.

A handout about warning signs in pregnancy does not mean the same thing to a low-risk nullipara at 12 weeks as it does to a patient with a prior preeclampsia diagnosis at 28 weeks. An explanation of fetal movement counting is different for a patient who has experienced a prior loss. A guide to labor preparation is different for someone who has had a prior cesarean.

Interactive tools can adapt to these individual variables. Static handouts cannot. This is the core value proposition of AI-assisted prenatal education.

Read more

Informed consent is the ethical foundation of clinical medicine. It is also, in practice, frequently reduced to a signature on a form that the patient has not had time to read, does not fully understand, and signs because the clinical environment implicitly communicates that this is what is expected.

This is not genuine informed consent. It is documentation of consent, which is a different thing. Interactive informed consent tools built with Claude cannot solve the structural problems that make genuine consent difficult in busy clinical settings. But they can significantly close the gap between what patients are told and what they understand. This course covers how.

Read more

Postpartum depression affects roughly one in seven new mothers, and screening rates, while improving, remain inconsistent. The tools exist: the Edinburgh Postnatal Depression Scale has been validated in multiple languages and across diverse populations. The barrier is not the absence of a good screening instrument. It is the absence of a workflow that makes screening consistent, results meaningful, and follow-up reliable.

A Claude-built postpartum depression screening dashboard can address all three of these gaps. This course explains how.

Read more

Gestational age calculation is one of the most fundamental tasks in obstetrics, and one of the most consistently confusing for patients. The concept of dating a pregnancy from the last menstrual period, the difference between gestational and embryonic age, the role of ultrasound in confirming or adjusting dating, and the implications of a discrepancy between clinical and ultrasound dating: none of these are intuitive, and most patients encounter them without adequate explanation.

A well-built gestational age tool designed for patient use can change that. This course covers how to build one that is accurate, clear, and genuinely useful for the patients you serve.

Why existing gestational age calculators fall short

There is no shortage of pregnancy due date calculators on the internet. Most of them do the basic math correctly: add 280 days to the last menstrual period, display a due date. What most of them do not do is explain the concept, communicate uncertainty, address the role of ultrasound dating, or help patients understand what their gestational age actually means clinically.

A patient who knows her due date but does not understand what gestational age means, why it matters, and how it might change based on an early ultrasound is not an informed patient. She is a patient who has a number without the context to use it. The tool you build should provide both.

Read more

Visual abstracts have changed how research findings circulate in medicine. A well-designed visual abstract can communicate the key findings of a study in a format that is sharable, scannable, and memorable in ways that a traditional abstract simply is not. For a Substack and LinkedIn presence like ObGyn Intelligence, visual abstracts are not just nice to have. They are the currency of modern medical communication.

This course covers how to build a semi-automated visual abstract generation workflow using Claude, including how to extract data from papers, design the visual output, and maintain the branding consistency that makes your content recognizable.

Why visual abstracts matter for clinical communication

The traditional research abstract serves a specific purpose in the academic ecosystem: it allows readers to decide whether to read the full paper. It is written for a specialist audience, uses technical language, and assumes familiarity with the research context.

A visual abstract serves a different purpose. It communicates the key finding to a broader audience in a format that works on a phone screen, that gets shared on social media, that can be understood by a clinician scrolling through their feed at 6 am, and that your patients might actually look at. These are not the same audiences, and they are not reached by the same format.

For a clinician who publishes on Substack and engages on LinkedIn, the ability to consistently produce high-quality visual abstracts is a professional differentiator. It signals that you understand how to communicate research, that you are current with the literature, and that you respect your audience’s time.

Read more

Clinical checklists have one of the strongest evidence bases in patient safety research. They reduce errors, standardize care, and serve as cognitive scaffolding during high-stress, high-stakes clinical moments. The challenge has always been that building a well-designed, evidence-based checklist is time-consuming, and maintaining it as evidence evolves is often neglected.

Claude changes both of those equations. This course walks through how to build a clinical decision support checklist for labor management that is evidence-based, appropriately formatted for bedside use, and maintainable over time.

What makes a clinical checklist actually work

Not all checklists are created equal. The checklists that reduce errors in aviation and surgery share specific design characteristics that distinguish them from the ones that become wallpaper, present in the room but never actually used.

Effective checklists are short. Research consistently shows that checklists exceeding ten to twelve items are less reliably completed than shorter ones. They are binary: each item is either done or not done, not maybe or sort of. They use the language of the clinical environment, the words clinicians actually use rather than formal documentation language. They are placed at the point of use, not in a binder somewhere. And they are owned by the team that uses them, not imposed from administration.

When you ask Claude to build a clinical checklist, specifying these design principles as constraints produces dramatically better output than asking for a checklist without them.

Read more