Every coding agent you’ve ever used: Claude Code, OpenClawd, Cursor’s agent mode, Devin, Hermes, the autonomous research assistants proliferating across HackerNews, etc., all run on the same machinery, the Agentic Harness.
In this post, we’ll build a basic Harness from scratch to understand every moving part. By the end, you’ll have a working bare bones agent and a clear mental model of what agents like Claude Code are actually doing under the hood.
We’ll look at how to build a more sophisticated production-ready harness in a future post.
You can also find the companion notebook on the LLMs for Data Science GitHub repository:
In the early 1950s, war raged over the Korean peninsula with American-made F-86 fighters being outmatched by the technically superior Russian-made MiG-15. Col John Boyd was the US Air Force fighter pilot in charge of trying to His main insight has proven useful ever since: You can make the combined US Pilot + F-86 system better than the Korean Pilot + MiG-15 system…
