Markdown source

Self-Improving Agents That Teach the Company Back

Conference Context

Session Description

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.

Media Evidence

No related AI Engineer channel video found yet.

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

No linked video, transcript, or slide source has been attached yet.

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

Transcript Status

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

People

Notes

Synthesis

Synthesized Breakdown

Self-Improving Agents That Teach the Company Back ## Conference Context - Date/time: 2026-06-29 · 12:05pm-12:25pm - Track/room: track TBD · Expo Stage 4 SE - Speaker(s): Rafal Wilinski - Session type/status: session · confirmed - Track: track TBD - Room: Expo Stage 4 SE - Session type: session - Status: confirmed ## Session Description 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.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.