boeckeler-2026-harness-engineering-fowler · post

Harness engineering for coding agent users

Created: 2026 · Ingested: 2026-09-11

https://martinfowler.com/articles/harness-engineering.html

Harness engineering for coding agent users To let coding agents work with less supervision, we need ways to increase our confidence in their result. As software engineers, we have a natural trust barrier with AI-generated code - LLMs are non-deterministic, they don't know our context, and they don't really understand the code, they think in tokens. This article explores a mental model that brings together emerging concepts from context and harness engineering to build that trust. Birgitta is a D

Referenced by

Claims in this catalog that draw on this source, and whether as support or counterpoint.

supportsThe agent that produced an artifact is a biased judge of it — it holds the context and the incentives that skew its assessment — so verification belongs with a deterministic sensor or a separate verifier that reports failures back rather than rewriting the output, and in a multi-agent system the verifier is the one component no agent may override.