Let your AI agent do its own harness engineering, with human approval
Cole Medin · youtube · 2026-10-21
Cole Medin shows how to let production agents perform their own harness engineering — learning from real conversations and proposing changes to their own rules, skills and memory — while you approve everything it learns.
- Core idea: apply the playbook that makes coding agents reliable (iterating memory, skills, rules) to any production agent.
- Two improvement loops: Loop 1 extracts lessons from escalations into memory; Loop 2 uses LangSmith Engine to propose harness changes automatically.
- Key design: per-user private memory, versions and rollbacks, Slack notifications — human stays in the driver's seat.
Built on LangChain's Managed Deep Agents and LangSmith Engine, with a full live demo and results.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23