R095 · AI education › Learning paths for AI engineers

Learn Harness Engineering: an open course with four production teardowns

Read the original

educationagent-harnessteachingmulti-agent

Source: walkinglabs/learn-harness-engineering README (MIT). Surfaced by Shubham Saboo.

What it is

A project-based course on what you build around a coding agent so it finishes the job reliably: the environment, state management, verification and control. 14 lectures and 8 projects, translated into 15 languages.

The framework

The course uses five harness subsystems: instructions, tools, environment, state and feedback. Everything else is organized around them.

Path through the material

Frontier harness teardowns (August 2026 section)

ProductHarness choices highlighted
Claude Codefour memory layers, five compaction levels, hooks, isolated sub-agents
Codexrepository as source of truth, AGENTS.md as a directory page, worktree isolation
Piminimal kernel, extend it by asking it to build what you need
DeepSeekeverything is a plugin, capability seams, an event pipeline

All four are read through the same five-part lens, so you can compare designs and borrow pieces.

Why it is worth a staff engineer's time

Caveats

R023 (building a coding agent from scratch), R087 (Stanford CS329Z), R006 (harness vocabulary), R054, R094.

Connections

See R095 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.