Teaching My AI Agent to Learn From Its Own Mistakes

## How I Built a Self-Improving Code Agent on a Mac Mini, Inspired by Databricks' KARL In early March, Databricks published KARL (Knowledge Agents via Reinforcement Learning), a system that trains enterprise search agents via reinforcement learning. They had 26 researchers, enterprise GPUs, and a proprietary base model. Their agent beats Claude Opus 4.6 and GPT 5.2 on enterprise search benchmarks at 33% lower cost. I read the paper and thought: what if I applied the same idea, not to enterprise search, but to the software engineering agent I use every day? And not on a GPU cluster, but on the Mac Minis in my living room? Five days later, I had 485 recorded trajectories, a 5-signal reward engine, a trained LoRA adapter, and a system that automatically learns from every coding session I run. Here's how it works, how it differs from the original, and what I learned. KARL's premise is simple: instead of hand-writing rules for how an AI agent should behave, you record what the agent actually does, score those recordings based on outcomes, and train on the best ones.