//www.martinrichards.me/tags/harness-engineering/ Recent content in Harness Engineering on Martin C. Richards Hugo en Fri, 24 Jul 2026 21:44:55 +0200 //www.martinrichards.me/post/whats_inside_the_harness/ Fri, 24 Jul 2026 21:44:55 +0200 //www.martinrichards.me/post/whats_inside_the_harness/ <h1 id="whats-inside-the-harness">What&rsquo;s Inside the Harness</h1> <p>In March I published <a href="https://www.martinrichards.me/post/building_your_own_agent_harness/">Building Your Own Agent Harness</a>. A harness, I said, is the skills, workflows, and methodology that teach your agent how you think and how you build. Since then, <em>harness</em> has taken on a different meaning: Claude Code, Codex, Cursor, the whole runtime wrapped around a model. In my terms, that combination is the agent. You can call it the harness too, but when you&rsquo;re building with an agent, it is the part you have the least control over. I&rsquo;m not going to fight the internet over what to call a harness. I care about what you put inside it.</p> //www.martinrichards.me/post/building_your_own_agent_harness/ Tue, 10 Mar 2026 00:00:00 +0000 //www.martinrichards.me/post/building_your_own_agent_harness/ <h1 id="building-your-own-agent-harness">Building Your Own Agent Harness</h1> <p>I&rsquo;ve been trying to write about coding agents for a while. Each time I sit down, the ground has shifted. The models change, my own workflow changes, and whatever I had to say feels stale before I finish saying it.</p> <p>But one thing has stayed constant through all of it: the agents that produce good work are the ones that know how I work. My conventions, my patterns, my preferences. The ones that fail are the ones I drop into a codebase with no context and expect to read my mind. Complaining that an agent wrote bad code without giving it any of that context is like calling a new hire incompetent on their first day because they didn&rsquo;t already know your codebase.</p>