LangChain: 70% of Managed Deep Agent runs now come from schedules, not humans
LangChain · x · 2026-10-29
LangChain says that since launching dynamic scheduling for Managed Deep Agents in September, over 70% of MDA runs on LangSmith come from schedules rather than a human typing a message; deploying a proactive agent takes just mda init and mda deploy.
The accompanying article argues most proactive agents are essentially cron jobs with a prompt: an agent writes its own prompt and schedule (e.g. checking Slack, email and calendar every 2 hours on weekdays), a cron server built into the LangSmith deployment fires the run, and results come back as a Slack DM. Overnight-dreaming memory and agents that ping you first are all scheduled runs built on a 50+ year-old OS idea.
More from coding & agent
- ChatGPT's dot can now text you via iMessage, with per-channel routing tips — nickbaumann_ · 2026-10-29
- Prevention beats repair: proactive AI saves ~$225K/year vs $120K for fix-it agents — louisdorard · 2026-10-29
- Product engineering in 2026: let Claude Code read the meeting transcript and build — curious_vii · 2026-10-29
- Anthropic researcher spends 3 straight workdays in Antigravity, vouches for Carbon — vedantmisra · 2026-10-29
- Microsoft launches Copilot harness in public preview within Foundry Agent Service — lee_stott · 2026-10-29
- Dev vibecodes a ComfyUI node that auto-archives and organizes all your generations — LaurentLaSalle · 2026-10-29