This workflow details a 'Super MVP' method for prototyping and testing a complex AI agent, like a personal morning briefer, directly in Cursor using only plain English instructions in a Markdown file. It's a powerful way for non-technical builders to create and iterate on AI product logic.
with Claire Vo
Begin by testing your core idea in a simple chat interface like ChatGPT. Use a repetitive daily prompt to understand the model's capabilities, limitations, and develop an intuition for its behavior.
Write me a morning briefing based on what you know about me.Move into Cursor and create a Product Requirements Document (PRD) and a Technical Design Document (TDD) for your AI agent. You can use Cursor's AI to help you draft these documents.
Create a Markdown file (.md) that contains the step-by-step instructions for your AI agent. This file is the 'Super MVP'—it acts as the application's source code, telling the AI how to behave, which tools (MCPs) to use, and what format to use for the output.
Run your AI agent prototype by simply referencing your instruction file in the Cursor chat pane. Cursor's AI will read the instructions and execute the steps, acting as the engine for your no-code application.
@super_mvp_agent_instructions run today's briefing.
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.