About this session

Agents forget too much. A run might solve a customer escalation, debug a deployment, or figure out the review pattern for a tricky code path, then the knowledge disappears into a transcript. At Runlayer, we started treating that knowledge as a product surface. Skills are reviewable, editable instructions that agents can load over MCP. An agent can start with a task, learn something useful while doing the work, and draft or update a private skill from that run. That skill loads into future runs for the same agent, stays inspectable by humans, and can eventually graduate into a team or org-level skill. The flywheel gets more interesting once a skill becomes useful beyond the agent that created it. A learned skill can move from one agent's private memory into shared organizational knowledge, then become available through the Runlayer plugin inside Claude Code, ChatGPT, and other AI clients employees already use. The agent does the work, captures the playbook, and the company gets better at that work everywhere agents are used. This talk walks through the architecture and product choices behind self-improving skills: post-run distillation, skill mutation tools, private-by-default scoping, runtime loading, UI inspection, promotion into shared skills, and the safety boundary between this agent learned something and everyone should now use it. The goal is an agent that leaves behind a better handbook for the next person, the next run, and eventually the whole organization.

Speaker