Series · 3 posts
Posts in the Harness Engineering series
When an AI Agent performs poorly, it's not necessarily because the model is dumb. Starting from a small experiment where a Gemma 4 2B fixes a bug, this piece explains what a Harness is, how Harness Engineering differs from Prompt / Context Engineering, and how effective natural-language rules like agents.md really are.
Three OpenAI engineers, five months, one million lines of AI-generated code, zero hand-written. The real value of this experiment isn't the numbers — it's the proof that Harness design can be engineered. Five concrete practices: making the app legible to agents, treating the repo as the source of truth, mechanizing architectural constraints, rewriting merge philosophy, and background entropy management.
Distilling Harness Engineering from concept and benchmark case into something you can start executing today: the four fixed failure modes of Agents, the 40% context sweet spot, the four-pillar framework the industry has converged on, and a three-phase roadmap from 'this afternoon' to 'fully automated in two weeks' — closing with six industry consensus points and three still-unsolved problems.