Skills are a great way to teach an agent a pattern. I got curious whether the agent could just learn the pattern, so I tried training a model while also figuring out what RL actually is.
Brian Douglas
Head of DX at Continue
Oakland, CA
I work at the Paper Compute Company.
Previously founded Open Sauced (joined Linux Foundation 2024) and led Developer Advocacy at GitHub.
Host of "Open Source Ready" and "The Secret Sauce" podcasts. Passionate about mentoring new open-source contributors.
Latest Posts
I built a tool that fans out parallel Claude Code agents to fix lint errors across a codebase. It taught me that the hard problems aren't prompts or models. They're isolation, observability, and memory.
How a DeepMind paper turned my Pokemon agent from 'watch and tweak' into 'run and measure.'
I was an hour deep into a Postgres integration when Claude Code crashed. No session recovery. But tapes had every message stored in a local SQLite database.
Agent sessions contain valuable wisdom worth preserving. Like magnetic tape archives knowledge for decades, Tapes preserves agent memory for lasting value.