The Codebase Is the Harness Pyn runs a monorepo in which the bots that modify its product code also modify their own harness — their markdown instruction files, databases and MCPs — so agents can update their own instructions after a fix, the company's engineering blog reports. In one example, an agent given access to PostHog session recordings diagnosed and fixed two bugs without intervention: a user making a change, clicking back and getting stale data, and a user unable to log in because the error message wasn't showing, with the review bot assisting. The author argues a human still supplies macro direction and self-improvement is currently only a carve-out, but that even a fraction of self-improvement applied to the system itself yields a compounding system. I have a growing belief that self-improving codebases are the end goal. Perhaps that self-improvement starts small and niche, but it can grow and compound. To get there a codebase has to understand itself to the extent necessary . That has changed what I think a "harness" is. The word usually means the wrapper around a model: the prompts, the tools and the loop that make it an agent. I've used it that way on this blog, and it's where half my day goes https://jonathannen.com/sharpening-the-axe/ . But to be self-improving it needs to be self-referencing. I now think the codebase is the harness. At Pyn https://www.pyn.ai we have a handful of bots that perform work on the codebase. They have their own markdown files, databases, MCPs and so on, and all of it is oriented toward the codebase. Even the code review process is part of the harness