Blog

Engineering deep-dives.

Design decisions and lessons learned building Chalie.

21 Apr 2026

The Meta-Harness, Two Weeks Later: From Interesting Experiment to Working Contributor

A follow-up on our self-improvement loop. We tore out most of the orchestration, made the kernel a single skill, and watched it open and merge multiple PRs in a single afternoon.

By Dylan Grech

6 Apr 2026

Building an AI That Improves Itself: The Meta-Harness

How we built an autonomous improvement loop that uses Claude Opus to analyze test failures, propose fixes, and create pull requests — with no human writing code.

By Dylan Grech