Harness engineering

Whether an agent does the job well doesn’t depend only on the model and the prompt, but also on the harness around the model: what project information it knows, what tools it can use, what boundaries it has, and how it checks the result when it’s done.

AGENTS.md or CLAUDE.md is more like onboarding notes — the entrance to a harness, not the whole thing. It only tells the agent what to know on entering the project; it doesn’t cover where to find information, how to complete the task, holding the boundaries, or recovering after a mistake.

Implementing harness engineering really is engineering-heavy, but once an agent can read data, call tools and act for users, the decisions about information, permissions, boundaries, acceptance and human intervention were always part of product design.