Learn how to prototype and build a production-ready application to automate the creation of massive FDA submission documents. This workflow takes you from a simple prompt in Claude to a functional Streamlit app with features like PHI redaction and cost analysis.
with Claire Vo
Treat Claude as a software engineer collaborator. Provide a high-level prompt outlining the problem, business impact, and desired outcome to generate a complete project plan, including step-by-step instructions, core capabilities, a demo script, and starter Python code.
The thinking I had in mind is that Claude is a software engineer, and I'm talking to them and trying to tell them why it matters like any good PM would, and trying to tell them what end product we wanna produce as a result.Instruct Claude to build the logic for detecting and redacting Protected Health Information (PHI) from unstructured clinical data. It can identify the correct models for medical named entity recognition and generate the necessary Python code and complex RegEx for pattern matching.
Wrap your Python script in a simple user interface using the Streamlit framework to make the tool accessible to non-technical colleagues. You can run the application locally from your terminal to quickly spin up a web app.
streamlit run app.pyAdd functionality to the app that summarizes the cleaned clinical trial data into the required Common Technical Document (CTD) format. Crucially, include options to download the output as both a standard text file and the proprietary XML format required for official submissions.
Build a feature directly into the app that tracks the token cost and duration for each operation (e.g., PHI redaction, document generation). This provides transparent data on the tool's ROI, making it easier to gain approval from stakeholders by directly comparing AI costs to manual processes.
Follow Sahil Lavingia's method for delegating small but impactful maintenance tasks, like fixing an internal Slack report, to the AI agent Devin. This workflow shows how to use simple, clear prompts to fix code and update system prompts without distracting your engineering team.
Learn Gumroad CEO Sahil Lavingia's process for rapidly prototyping a UI with v0, then using the AI agent Devin to autonomously code, implement, and submit the feature for review, turning a multi-day task into a one-hour workflow.
Improve your writing in real-time by using ChatGPT as a first reader. Get instant feedback on structure, clarity, and flow as you write, allowing you to polish your work section by section.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.