Guides
The craft of building with AI
Not steps — judgment. Opinionated playbooks on how to actually work with a coding agent, ship fast without shipping junk, and get better at the parts the AI can't do for you.
Write a rules file your agent respects
Every coding agent — Claude Code, Cursor, Windsurf, Copilot — reads a rules file before it touches your code. Most people write theirs like a wishlist and then wonder why the agent ignores it. A rules file is not documentation; it's a control surface. Here's how to write one the agent actually obeys.
Read the guide →- Prompting · 9 min read
Prompt patterns for coding agents
Coding agents like Claude Code, Cursor, and Codex don't fail because the model is dumb — they fail because you gave them a wish instead of a spec. This is the craft of turning "make it work" into instructions an agent can actually execute, verify, and not wander off from. Learn these patterns and your hit rate goes from "roll the dice" to "ship it."
Read → - Shipping · 9 min read
From idea to deployed in a weekend
Most "build in a weekend" advice fails because it optimizes for the demo, not the deploy. This is the opposite: a playbook for actually shipping something real people can use by Sunday night — scoped tight, wired to boring proven tools, and live on a URL. The craft is in what you refuse to build.
Read → - Debugging · 9 min read
Debug with AI without going in circles
Debugging with an AI assistant fails the same way every time: you paste an error, it guesses, you paste the new error, it guesses again, and forty minutes later you have three "fixes" layered on top of a bug you still don't understand. The problem is never the model — it's that you handed it a symptom and asked for a cure. This guide teaches you to run the loop like an engineer, so the AI amplifies your diagnosis instead of replacing it with confident nonsense.
Read → - Decisions · 9 min read
Choose your stack in 2026
Picking a stack in 2026 is less about finding the "best" tools and more about picking tools that agree with each other — and with the AI writing most of your code. The right stack is the one with the deepest training data, the tightest integrations, and the fewest custom abstractions your model has to guess at. This is the playbook I'd hand a vibe coder shipping their first real product.
Read → - Working with agents · 11 min read
How to actually work with a coding agent
A coding agent is not a vending machine you drop a wish into. It's a fast, literal, tireless junior engineer with no memory of yesterday and no instinct for your codebase. The difference between people who ship with agents and people who fight them all day is almost entirely about how you set up the work, not which model you pay for. This is the playbook.
Read → - Quality · 9 min read
Review AI-written code safely
AI writes code fast, and fast is exactly the problem: a plausible-looking diff can hide a security hole, a silent data-loss bug, or a dependency that doesn't exist. Reviewing AI-written code isn't the same as reviewing a coworker's PR — the failure modes are different, and so is the craft. This is the playbook for reading what the model gave you before it reaches production.
Read → - Shipping · 9 min read
The pre-launch checklist
Shipping isn't a button you press — it's the moment your app stops being forgiving. Locally, you are the only user, you never abuse your own forms, and every secret sits safely in your head. The pre-launch checklist is the discipline of imagining a hostile, careless, curious stranger using the thing you built, and closing the gaps before they find them.
Read → - Judgment · 8 min read
When NOT to reach for AI
AI can write most of your code, but it cannot own the decisions that make code correct, safe, or legal. This is a playbook for the moments when reaching for the model is the expensive move — where its confidence is a liability and your judgment is the actual product. Learn to recognize these situations by feel, before they cost you a weekend or a customer.
Read → - Learning · 9 min read
From no-code to code
You already build things — you just build them in Bubble, Webflow, Zapier, or by pasting prompts into a chat window until something works. Moving to real code isn't about abandoning that instinct; it's about learning where the abstractions you've been renting actually live, and taking ownership of them one layer at a time. This is the playbook I'd give a no-code builder who's ready to stop hitting walls.
Read → - Architecture · 9 min read
Structure a project an agent understands
An AI agent reads your codebase the way a new hire does on their first day — except it can't grab coffee with a teammate to ask "wait, where does auth live?" The structure IS the onboarding. This is a playbook for shaping a project so an agent (and future-you) can navigate it, change it safely, and not hallucinate its way into a mess.
Read → - AI · 9 min read
Add your first AI feature
Your first AI feature is not a chatbot. It's a small, boring, well-bounded task inside your existing app that a language model happens to be very good at — and the difference between something that ships and something that embarrasses you in production is almost entirely in the plumbing around the model, not the model itself. This is the playbook for wiring one in without shooting yourself in the foot.
Read →
Keep exploring
More of the library
- 383tools→Tools
Every tool, with an honest take on each.
- 8stacks→Stacks
Tool combinations that work together.
- 10showdowns→Comparisons
Honest head-to-heads with a verdict.
- 22recipes→Recipes
How to build the thing you keep needing.
- 6paths→Learning paths
An ordered route through the library.
- 40prompts→Prompts
Reusable prompts worth stealing.
- 10ideas→Build ideas
Project blueprints with a stack to match.
- 52terms→Glossary
Plain-language words for what AI writes.
- 10notes→What's new
The shifts worth knowing about.