LangChain ships Managed Deep Agents with containerized evals via LangSmith
LangChain · x · 2026-09-11
LangChain launched Managed Deep Agents with @harborframework, tackling a key agent pain point: knowing whether adding skills, swapping models, or tweaking tool descriptions broke existing behavior. Evals run in a fresh container every time and are tracked in LangSmith. A 9-minute explainer video accompanies the release.
More from coding & agent
- HeyGen Open-Sources Real-Time AI Avatar Framework Built on OpenAI's GPT-Live, With Language Tutor Demo — HeyGen · 2026-09-11
- Community challenge pits MLX vs CUDA to speed up local Qwen 3.8 Flash on DGX Spark — gajesh · 2026-09-11
- Tako data index lands in Vercel AI Gateway with one-line websearch integration — williamLberman · 2026-09-11
- Reading papers by walking: agents run experiments while you ask questions — yaroslavvb · 2026-09-11
- Stop pasting errors into AI chat: use MCPs for better Spark debugging — rseroter · 2026-09-11
- alphaxiv urges researchers to swap Claude Code/Codex for open models, citing OpenAI and Anthropic lock-in incidents — AdaptiveAgents · 2026-09-11