Learn how to use AI
A structured path from "what is an LLM" through verifying output, using AI at work, and building with it. Pick the path that matches where you are.
Pick your path
Start with the foundations
What AI is, what it gets wrong, which model to pick, and how to prompt well. A guided reading order if you are new to AI.
Start hereUse AI for your daily work
Task-based playbooks for email, meetings, research, weekly reports, and second-brain capture. Concrete setup, real tools.
Start hereBuild software with AI
From vibe coding your first app to working with AI on a real codebase. The four ways AI fits into building: prompts, skills, workflows, agents.
Start hereSequenced routes through the library
Three multi-guide paths shaped by role and goal: operator, engineer, PM. An ordered reading list with notes — work through it at your own pace.
Browse all categories
Working with AI
How to use AI for real work. From "what is an LLM" through verifying output, using it in your week, and building with it.
Building & shipping
Validation, distribution, and getting paid. The non-code half of putting something into the world.
Prompt Engineering
How to write prompts that work — from basic patterns through advanced techniques and building AI-powered products.
Stacks & systems
How modern tools fit together. Choosing, connecting, and automating across the stack.
Recently updated
Getting structured output: JSON, lists, and formats that hold
Why models drift from requested formats and what actually fixes it. How to get reliable JSON, tables, and structured lists — with and without native structured-output APIs.
Role prompting: how to assign a persona that actually steers behavior
The difference between system-level personas and inline "act as" instructions. When role assignment changes output quality, when it's theater, and the failure modes that make output worse.
Prompt chaining: how to break complex tasks into reliable steps
Why one long prompt fails where a chain of short ones succeeds. How to pass outputs as inputs, where to put the split points, and when chaining is overkill.
Chain-of-thought prompting: when reasoning out loud changes the output
Why telling a model to "think step by step" works, and when it doesn't. Zero-shot CoT vs few-shot CoT, what tasks benefit most, and the cases where it actively slows you down.