Learning paths
A route through the library
Not sure where to start? Follow a path. Each one is an ordered sequence of recipes, guides and glossary terms that builds you up from where you are to where you want to be.
- Beginner
Vibe coding 101
A meta-skills path that teaches the craft of building software with an AI agent, not one specific feature. You start from zero, learn how to actually direct a coding agent, keep it on the rails, debug and review its output, then take a project all the way to a live URL. By the end you can go from an idea to a deployed app without flying blind.
9 steps → - Beginner
From no-code to code
A ten-step arc that takes you from clicking around in no-code tools to shipping a real, code-based app with an AI agent as your pair. You'll pick a stack, learn to drive an agent, build and deploy something end-to-end, then add the parts real apps need — a database, auth, debugging, and a launch check.
10 steps → - Beginner
Understand your stack
A conceptual-but-grounded tour of the layers that make up a modern 2026 web stack, from the UI you see down to where your code runs. By the end you'll be able to name every piece of a Next.js + database + serverless setup and explain how they connect — so when your agent scaffolds a project, you actually know what you're looking at.
10 steps → - Intermediate
Ship your first SaaS
This path takes you from "I can build screens" to "I have a SaaS people can sign up for and pay me." You'll lock in a stack, stand up the data and auth layer, wire Stripe billing and transactional email, then harden and ship with secrets, a pre-launch pass, deploy, error tracking, and analytics. Follow it in order and each step assumes the previous one is done.
10 steps → - Intermediate
Add AI to your app
A build-up path that takes you from "I've never called an LLM" to shipping an AI chat feature, then grounding it in your own data with RAG, then hardening it for production. You learn the handful of AI concepts that actually change how you build, in the order you hit them, and end with the cost/reliability controls that separate a demo from a live feature.
10 steps → - Intermediate
Get dangerous with a coding agent
This path makes you dangerous with a coding agent — not by teaching one framework, but by teaching the loop: how to drive the agent, constrain it, and catch its mistakes. You'll go from "it wrote something, I guess I'll run it" to steering a fast, reliable build-review-ship cycle, ending with a real weekend project deployed.
9 steps →
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.
- 12guides→Guides
The craft of building with AI.
- 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.