All learning paths

AI learning path

Coding with AI

Use coding agents and assistants as collaborators without losing engineering judgment.

Best for
Software developers
Level
Intermediate
Time
8-16 hours

Choose this when

You already code and want AI to help with feature work, tests, reviews, and maintenance.

You should be able to

You can give agents better context, constrain scope, run checks, and review generated code critically.

Checkpoint

Move on when you can spot plausible but wrong AI code before it ships.

Do

Learning sequence

This is the route through the topic. Watch and open the material inside the step where it is used.

Search resources Search videos

Step 1

Set the context

Give the agent repo conventions, commands, constraints, and a narrow target.

  • Repo map
  • Commands
  • Scope

Open here

Claude Code overview

Guide · Anthropic · Intermediate

You want practical docs for using Claude as a coding agent across a real codebase and toolchain.

Open resource

Step 2

Work in feedback loops

Ask for tests, run checks, review diffs, and keep changes small enough to understand.

  • Tests
  • Diff review
  • Iteration

Watch here

AI tools for software engineers without the hype

Simon Willison

Use this for sober judgment about where AI coding helps or fails.

Open here

OpenAI Codex

Official product docs · OpenAI · Beginner to advanced

You want the current OpenAI path for agentic software engineering, code review, and background coding tasks.

Open resource

Step 3

Raise the quality bar

Use agents for refactors, docs, migrations, and review only when verification is clear.

  • Refactors
  • Review
  • Regression checks

Watch here

20 Tips to Master Claude Code in 35 Minutes

Peter Yang

Tactics for tightening feedback loops once the basics are clear.

Open here

AI Skills for Real Engineers

Skills catalog · Matt Pocock · Intermediate

You want a reusable skill system for agentic coding, including /grill-me, /grill-with-docs, /to-prd, /to-issues, /tdd, /triage, /handoff, /prototype, and review workflows.

Open resource

Practice task

Pick one bug, ask AI to explain the code path, write or update a test, implement, and review the diff yourself.

Reference

All resources in this path

Search resources

Step 1

Claude Code overview

Guide · Anthropic · Intermediate

You want practical docs for using Claude as a coding agent across a real codebase and toolchain.

Step 2

OpenAI Codex

Official product docs · OpenAI · Beginner to advanced

You want the current OpenAI path for agentic software engineering, code review, and background coding tasks.

Step 3

AI Skills for Real Engineers

Skills catalog · Matt Pocock · Intermediate

You want a reusable skill system for agentic coding, including /grill-me, /grill-with-docs, /to-prd, /to-issues, /tdd, /triage, /handoff, /prototype, and review workflows.

Educators to follow

Simon Willison profile photo

Simon Willison

Beginner to advanced

Read the recent model-roundup posts, then try the llm command-line tool with two or three different providers.

View educator
Matt Pocock profile photo

Matt Pocock

Beginner to advanced

Use LLM Fundamentals or the AI Engineer Roadmap if you need concepts, the Vercel AI SDK Tutorial or AI SDK v6 Crash Course if you want to build apps, and the AI Skills catalog if you want practical agent workflows like /teach, /grill-me, /tdd, and /triage.

View educator
Swyx profile photo

Swyx

Intermediate to advanced

Watch AI Engineer talks for production patterns and tool choices.

View educator
Andrew Ng profile photo

Andrew Ng

Beginner to advanced

Start with ChatGPT Prompt Engineering for Developers, then pick a RAG or agents course.

View educator