LangChain shares lessons on building proactive agents, launches Managed Deep Agents

LangChain · x · 2026-11-18

LangChain's team distilled lessons on building proactive agents: unlike chat-only agents, proactive agents need explicit triggers for autonomous action:

These triggers let agents act far beyond a chat interface, making them far more valuable organizationally. They also launched Managed Deep Agents (public beta on LangSmith Cloud): you write instructions, tools, and skills and pick a model, while the platform runs the Deep Agents harness (planning loop, tool calls, filesystem, subagent delegation) and runtime, with memory, channels, and schedules built in as first principles.

Original post →

More from coding & agent

coding & agent channel →