Step-by-step workflows from real experts. Each workflow includes prompts, code snippets, and practical tips.
View all How I AI episodes
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.
Go from an empty folder to a playable 3D multiplayer prototype in about 15 minutes. This advanced workflow leverages the Claude command-line interface and parallel development to rapidly build and debug both the frontend and backend of a flight simulator game.
Learn to build a complex 3D multiplayer game, even with no prior game development experience. This workflow guides you through an iterative process of using an AI assistant like Cursor and Claude as a junior developer to go from a simple concept to a functional prototype.
Use Repo Prompt to gain surgical control over your AI's context. This workflow shows you how to manually select specific code files, combine them with a detailed prompt and a persona, and generate a highly-contextualized input for an LLM like Claude or Gemini.
Learn how to configure Machine Control Protocols (MCPs) in Cursor to control external tools like a headless browser or a database directly from your IDE using natural language commands, effectively reducing context switching and manual work.
Learn how a non-engineer built a custom, high-quality website translation service using an AI-native code editor and GitHub Actions. This workflow replaces expensive localization software and agencies, saving over $140,000 annually while improving translation quality and speed.
Take a detailed product blueprint and use the Replit AI agent to build, iterate, and deploy a complex, database-driven web application. This workflow demonstrates how to guide the AI through conversational prompts to create a functional app without deep coding knowledge.
Adopt a structured, software engineering-inspired approach to iterating on AI designs. Use forking to safely explore new ideas and apply a two-step debugging prompt to reliably fix errors without frustrating back-and-forth.
Use AI to analyze test logs, identify and prioritize technical debt, and generate a task list for AI agents like Cursor or Devin to systematically fix issues. This creates a repeatable process for improving codebase health.
Unify scattered documentation into a single repository directory. This creates a single source of truth, improving consistency and efficiency for both human engineers and AI agents.
A developer-focused guide on creating a new capability for the Goose AI agent. Learn to write a simple Python script, wrap it into a reusable Model Context Protocol (MCP) for sending emails, and integrate it into a larger workflow.
When your engineering team hits a deadlock on a new project, use an AI tool like Rork to build a functional mobile prototype. This provides a concrete vision that can unblock the team and generate new implementation ideas without writing any code.
Integrate Devin AI with your alerting system like PagerDuty to act as a first responder for incidents. Devin automatically investigates issues, analyzes logs, and generates an initial report to accelerate triage and resolution by your engineering team.
Leverage Devin AI as an always-available resource to quickly handle frontend UI adjustments like button styling or spacing. Devin implements the changes and provides before-and-after visuals, drastically speeding up the review and iteration cycle.
Use Devin AI as a junior engineer to integrate a new server into an existing codebase. This workflow combines DeepWiki for codebase analysis and a detailed prompt to guide Devin, which then handles research, coding, and pull request generation asynchronously.
Implement a disciplined, three-phase AI development cycle using Cursor and Xcode to build complex applications. This workflow uses custom rules for creating requirements, reviewing plans, and executing code in small, manageable steps to ensure high quality and maintainability.
Set up a coding environment with 'guardrails' like TypeScript and linters, then use a simple prompt in Cursor to let its AI agent automatically find, analyze, and fix code errors. This workflow streamlines debugging and improves code quality.
A structured, data-driven workflow for improving AI product quality by logging real user traces, manually analyzing errors, creating targeted evaluations (evals), and iterating on prompts or models.
Move your custom Claude Skills from your local development environment to the user-friendly Claude.ai web interface. This guide shows you how to package your skill folder, upload it, and begin using it for daily tasks directly in your browser.
This workflow demonstrates how to use a previously created 'meta-skill' within the Claude Code command-line interface to generate a new, specific skill. You'll learn how to prompt Claude Code to build a skill and then immediately test it.
Learn the author's preferred method for building a powerful 'meta-skill' inside the Cursor editor. This workflow uses Anthropic's official documentation to create a reusable agent that can quickly generate new, well-structured Claude Skills on demand.
Learn to go from an empty folder to a functional Next.js web application. This beginner-friendly guide uses Cursor's AI Agent to scaffold, run, and set up version control for your first project hub.
Learn to 'vibe code' a personalized party hub app using Lovable for the structure, Google Fonts for typography, and Midjourney for custom visuals. This workflow takes you from a generic AI template to a unique, 'farm-to-table' application with custom features like dietary restriction tracking.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.