learn-harness-engineering

Project-based course on harness engineering for coding agents: 14 lectures, 8 projects on tools, state, verification and loops, plus breakdowns of Claude Code, Codex and Pi. 15 languages.

19,706 2,159 TypeScript MITupdated 10 days ago

coding agents

View on GitHubDispute this mapping →

Curator's take

Best structured on-ramp if you use coding agents daily and want to understand why they fail on real work — every project evolves the same Electron app, and the frontier breakdowns map the course's five subsystems onto Claude Code, Codex, Pi and DeepSeek Harness. It teaches; it ships no runtime. Already building harnesses? Go straight to primitives like cwc-long-running-agents.

Mapped by ShipWithAI editors · links verified

Continue your stack

What teams reach for next — and why each earns a place beside learn-harness-engineering. Ranked by curator confidence.

pairs wellalternativebuilt withpick a node for the why · open it from the panel

README.md1 min read

A project-based course on building the environment, state management, verification, and control mechanisms that make AI coding agents work reliably.

🌍 This course is available in 15 languages: English, 简体中文, 繁體中文, 日本語, 한국어, Español, Français, Русский, Deutsch, العربية, Tiếng Việt, Oʻzbekcha, Türkçe, Portuguese (BR), Українська. Choose your language from the badges above.

🆕 What's New — August 2026

Frontier Harness Design Breakdowns — new section (4 breakdowns)

What	Details
New section	Frontier Harness Design Breakdowns — Apply the course's five-subsystem framework (instructions, tools, environment, state, feedback) to reverse-engineer how four frontier products build real harnesses.
Pi	[How Pi builds its harness](docs/en/harness-