Build better products with AI by following proven practices.
Practical application-building and product-development best practices for planning features, shaping data, setting boundaries, shipping safely, and turning prototypes into real software.
Pick a best practice before you ask AI to code.
Each best practice focuses on one decision you make before or during a build. The goal is to keep the product clear enough that an AI agent can help without quietly inventing the wrong app.
I was reading this comment on Hacker News:
Automating Git commit messages with AIOne of the most useful applications of AI that has done a positive change in my life is automating Git commit messages.
Save your prompts as docsWhen you finish a project, save the prompts you used.
Prompt in your native languageThis one is for those non native English speakers.
Let the AI test in Cursor's browserCursor has a browser built in. The AI can open it, navigate to your local dev server, click around, take screenshots, and report back.
Paste the error verbatimWhen something breaks, don't paraphrase. Don't write "the form isn't working." Don't say "there's some kind of database error."
Ask the AI to review its own workWhen you're happy with what you've built, ask the AI one more question:
Use screenshots. Words are slow, pictures are fastWhen something looks wrong, I don't describe it in a paragraph. I take a screenshot, drop it into the chat, and write five words.
Use the app, the next prompt will show up in your mindThe fastest way to find the next prompt is to use the app yourself.
Plan in plan mode, then build iteratingFor anything bigger than a one line tweak, I usually split building into two phases:
Pick a simple stackAfter 10 weeks of building with Cursor, I have a clear pattern. The projects that flew used a stack the AI could easily master. The projects that dragged use...
Write the first prompt like you're explaining the app to a friend at dinnerWhen you start a new project with AI, your first prompt sets the shape of everything that follows.
Deploy on day one, not at the endOne thing I see people make with AI built apps: they build the whole thing locally, then try to deploy at the end.
Build a CLI alongside the UISome projects I built with AI got a small CLI tool, in parallel with the web UI.
Use MCPs as backend superpowersMCPs aren't just for design. They turn the AI into someone who can operate your whole stack.
Pull design from a real design tool via MCPThere's a step beyond "screenshot the reference" to create a design: you can hand the AI a real design from a real design tool.
Use AGENTS.md as the project's memoryYour conversation with the AI ends when you close the chat. The next session starts cold.
Best practices are part of the Cook with AI library.
Get product best practices alongside guides, tutorials, developer tools, and workflow material.