Open-source course says the harness, not the model, can push a coding agent into the top 5
strickvl · x · 2026-07-23
A new open-source course, Building a Coding Agent From Scratch, focuses on one key lesson: the harness matters as much as the model.
- It cites LangChain’s Terminal-Bench experiment, where changing only the harness moved the same model from around 30th place to the top 5.
- The course teaches you to build a full coding agent in Python, starting from a bare agent loop.
- The project, called Decode, gradually expands into a swarm of remote agents running in parallel in the cloud.
More from coding & agent
- Multi-agent systems fail less on reasoning than on orchestration, says one production team — njanChe1 · 2026-07-23
- OpenCode PR #38484 adds a “Jump user message” flow — CryptoAlchemik · 2026-07-23
- Kimi K3 reportedly found 19 Redis 8.8.0 zero-days in 1.5 hours — evilsocket · 2026-07-23
- AI agents need cryptographic provenance, not just better reasoning — RileyRalmuto · 2026-07-23
- Live stream breaks down a loop-engineering agent workflow using skills and MCP — marlene_zw · 2026-07-23
- MCPs may be more typed, but skills cost more tokens and fail harder on bash — Vjeux · 2026-07-23