Rafal Wilinski explains why long-running agents need reusable skillsAn AI agent skill is a reusable package of instructions, resources, and tool guidance for performing a bounded kind of work. rather than repeatedly rediscovering procedures. He identifies developer-centric interfaces, authoring effort and fragmented client support as barriers, and proposes governed MCPModel Context Protocol is a standard way for AI applications to connect to external tools and sources of context. distribution as a shared access layer for technical and nontechnical users.
Rafal Wilinski connects trace-based skill creation with Voyager's reusable Minecraft procedures. His approach distills successful and failed runs into actionable instructions, with a focused example improving a task's reported success rate from 36% to 100%; the result is an example, not a general reliability guarantee.
Rafal Wilinski argues that organizations should retain procedural knowledge as frontier models changeAI agent memory is stored information that an agent can retrieve and use across steps, sessions, or changing contexts.. Sharing vetted lessons across agents could create a compounding knowledge loop, but stored tracesAn execution trace records the sequence of operations and results produced while a system carries out a task. and generated skills still need privacy checks, security boundaries and review before wider useHuman judgment in AI is the accountable interpretation and decision-making people contribute when setting goals, evaluating evidence, and managing consequences..
Watch on YouTube




