Design and refine a conversational AI by starting with ideal user dialogues in Claude. This workflow takes you from writing sample conversations to generating a fully interactive, LLM-powered prototype with a system prompt.
with Claire Vo
Begin by writing out 'golden conversations'—ideal sample dialogues between a user and your AI assistant. Use a detailed prompt in an LLM like Claude to set the scene, define roles, and specify desired features.
write a complete sample conversation between the consumer and AI assistant, where we want consumers to be able to upload their photo. Add some scenario requirements, like we want the assistant to analyze the photo, maybe provide some suggested replies, and continue that back and forth until they have enough info to submit quotes. Use assistant colon, user colon for labels. Write it as one continuous conversation.Upload real-world images or data to test how the LLM handles them within your defined conversation flow. Generate more examples for different use cases to identify patterns and ensure the flow works across various scenarios.
Now create more examples based on these images. Label each conversation with a title and a number at the top.Review the generated conversations for qualitative aspects like image recognition quality, conversational flow, conciseness, and tone. Provide direct feedback to the LLM to refine the dialogue, such as adjusting the AI's tone or avoiding certain topics.
rewrite these conversations based on this feedbackUse a feature like Claude Artifacts to turn your refined conversations into a working, interactive prototype. This step also generates a system prompt based on your examples, offering a fantastic way to learn how to write effective LLM instructions.
create an assistant app as an artifact, have a chat interface where the AI responds using the LLM that powers Claude. And then also create system prompt that is based on these example conversations. And then analyze these, uploaded photos, and include a camera icon in the input.
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.