Harness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayer
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
Why it matters
Explains why coding agents keep shipping green tests atop deteriorating architecture — a reward-function limitation, not a agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → or scale problem — and gives a concrete up-front planning workflow to keep AI-assisted codebases maintainable without slowing down.
Key quotes
“no amount of harness engineering or loops maxing can solve what is fundamentally a model training issue”
Dex Horthy
“Verifying code quality and maintainability is orders of magnitude harder than the code runs and the test pass. Because the cost function of bad architecture is measured in months and years.”
Dex Horthy
“if the model knew what good code looks like, it would probably write it in the first place”
Dex Horthy
“If you're drowning in PRs, you actually have too many bad PRs.”
Dex Horthy
“30 minutes over here in pre-planning and alignment can save you hours in review”
Dex Horthy
Chapters
0:00The narrative: you are the bottleneck, just ship more
1:28The cracks: outages and falling PR review quality
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
