We're sorry but this app doesn't work properly without JavaScript enabled. Please enable it to continue.

Learn AI Coding

Master the ins and outs of agentic coding as you build a Python interpreter. Learn how to ship code at scale while maintaining an impeccable codebase.

Browse Lessons

What you'll learn in this OpenCode course

Learn to use agentic AI tools effectively as a software engineer, not just a vibe coder. You'll understand how models, tools, prompts, context, rules, skills, MCP servers, and plugins all work under the hood. Coding agents let you ship code faster than any human could before. But without a talented human developer overseeing them, AI will make codebases worse, and bad code plus AI means more bad code.

Chapter List

1
Agent Harness
Install OpenCode and see how coding agents differ from chat and autocomplete, whether you run them in a terminal, a GUI, or on a remote server.
2
Models and Providers
Pick the right model for the job without lighting money on fire. Compare providers, token costs, reasoning models, and open-weight options you can host yourself.
3
Tools
Agents are only as useful as the tools they can call. Use the built-in tools, write your own, and lock things down with permissions and sandboxing.
4
Prompting
Write focused, well-scoped prompts, and learn when to plan, steer, cancel, or queue work while an agent is running.
5
Agents
Build custom agents and subagents for specific jobs, each with its own prompt, tools, step limits, and permissions. Plus, when (rarely) to touch temperature.
6
Context
Context is the agent's working memory, and it fills up fast. Manage sessions, compaction, forking, and undo so your agent doesn't lose the plot.
7
Rules
Give every agent session the same project knowledge with a well-written AGENTS.md file that you keep up to date.
8
Feedback Loops
Type checkers, formatters, and tests let an agent catch its own mistakes before you have to.
9
Skills
Package your repeatable workflows as skills, custom commands, and dynamic prompts, and figure out when a skill beats a tool or a dedicated agent.
10
MCP
Connect agents to outside services with the Model Context Protocol, including OAuth and code mode, without stuffing your context window full of tool definitions.
11
Computer Use
Let agents click around in a real browser using accessibility trees, vision models, Playwright, and Chrome DevTools.
12
Plugins
Extend OpenCode with your own hooks, transforms, and tools, then publish your plugin for other developers to install.
13
Best Practices
You're still accountable for every line an agent writes. Debug with evidence, refactor safely, ship small changes, and run multiple agents without making a mess.

Join 88 students in the Learn AI Coding course

Read reviews of their learning experiences

Great course overall, gently introduces you to AI Coding ('vibe-coding'?) and I like that Opencode doesn't even require an account :) Definitely worth doing!

(5/5)
Aduneer profile image

Aduneer

Germany

Browse Lessons

or view more reviews

Mediocrity doesn't cut it anymore

The only way to become a great developer is to write a lot of code

Avoid tutorial hell

by writing a ton of code

Stay motivated with

a game-like curriculum

Build portfolio projects

to prove your skills

Delve deeper

into foundational concepts

Learn flexibly online

without interrupting your life

For 1% the price of college

to minimize your financial risk

Frequently asked Questions

Got questions? We've got answers

Yes! It's free to create an account and start learning. You'll get all the immersive and interactive features for free for a few chapters. After that, if you still haven't paid for a membership, you'll be in read-only (content only) mode.

Platform

Boot.dev on X/TwitterBoot.dev on YouTubeBoot.dev on LinkedInBoot.dev on InstagramBoot.dev on TikTokBackend Banter Podcast

Languages

Subjects

Support

Pricing

Community

boot.dev
© Boot.dev 2026