LangChain's Interrupt keynote ships LangSmith Engine v2, Deep Agents 0.8, fine-tuning and more
LangChain · x · 2026-09-24
LangChain rounded up five announcements from Harrison Chase's Interrupt keynote:
- LangSmith Engine v2: red teaming and automated testing;
- Managed Deep Agents 0.8: new auth, memory and channels;
- LangSmith Trajectories: a readable view of every agent session;
- LangSmith Fine-Tuning: fine-tune models on agent data;
- LangSmith Custom Apps: build custom interfaces around your agent data.
More from coding & agent
- Pokee Isaac agent claims up to 10M-token context without summarizing — Kyrannio · 2026-09-24
- Dev builds AI-powered character animation tool, pushing ThreeJS + WebGPU limits — OpenAIDevs · 2026-09-24
- Prioritize real buyer language over LLM-generated prompt lists, developer advises — nikvassev · 2026-09-24
- Contrastive Language Model is 9x faster than Jev, sets SOTA on agentic coding benchmarks — iamrobotbear · 2026-09-24
- User claims Claude-built Polymarket copytrading agent turned $2K into $10.5K overnight — Aiden_Tech_Ai · 2026-09-24
- Building a PowerShell agent harness: model routing by prompt with explicit tool permissions — dfinke · 2026-09-24