- 1 Your harness, your memory ↗
- 2 Previewing Interrupt 2026: Agents at Enterprise Scale ↗
- 3 Deep Agents Deploy: an open alternative to Claude Managed Agents ↗
- 4 Human judgment in the agent improvement loop ↗
- 5 Better Harness: A Recipe for Harness Hill-Climbing with Evals ↗
- 6 Deep Agents v0.5 ↗
- 7 Arcade.dev tools now in LangSmith Fleet ↗
- 8 Continual learning for AI agents ↗
- 9 How My Agents Self-Heal in Production ↗
- 10 Open Models have crossed a threshold ↗
- 11 March 2026: LangChain Newsletter ↗
- 12 Announcing the LangChain + MongoDB Partnership: The AI Agent Stack That Runs On The Database You Already Trust ↗
- 13 Agent Evaluation Readiness Checklist ↗
- 14 How Kensho built a multi-agent framework with LangGraph to solve trusted financial data retrieval ↗
- 15 How we build evals for Deep Agents ↗