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:
- Real-world events: a new email or a newly opened pull request
- Developer-set schedules: a nightly memory update or weekly stale-PR sweep
- Agent-set schedules: a follow-up reminder or a user-requested daily brief
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.
More from coding & agent
- New plug-ins appear in Google's Antigravity IDE — DynamicWebPaige · 2026-11-18
- Cloudflare's Clairic extraction model returns confidence scores and spans, no preset categories — altryne · 2026-11-18
- Execution is cheap now, so be bolder with your UI design explorations — jh3yy · 2026-11-18
- Salesforce brings rich interactive experiences to Slackbot via Headless Experience Layer — msrivastav13 · 2026-11-18
- Agent Manager: a weekly agent that audits all your other agents, with sample prompt — nlarusstone · 2026-11-18
- Solo game studio runs ~20 AI teammates, goes from 50 to 1,900 PRs/week and 6x revenue — gdechichi · 2026-11-18