LangChain: scheduled runs hit 84% of agent runs after five weeks deployed
LangChain · x · 2026-11-21
LangChain engineer Caspar shared deployment data showing persistent agents are the trend: the share of agent runs started by a schedule in deployed multi-agent apps climbs from 33% in week 1 to 73% in week 2 and 84% by week 5. Useful agents work on their own time. CEO Harrison Chase teased season two of the Max Agency podcast on proactive, persistent, always-on agents.
More from coding & agent
- Dev insight: the most important part of agent harnesses is stopping AI shortcuts — clemnt · 2026-11-21
- Jeremy Howard: tying Neon to Antigravity will limit its success — jeremyphoward · 2026-11-21
- World's first AI Community Note writing competition open, $10k prizes, entries due Dec 8 — NathanpmYoung · 2026-11-21
- Higgsfield launches GPU Harness: rent on-demand GPUs inside Claude and ChatGPT — piotrbinkowski · 2026-11-21
- foldkit Derives Frontend Commands and Live Subscriptions from the Same Domain API — samgoodwin89 · 2026-11-21
- Dev One-Shots vercel/board with Alchemy Domain Deriving API, MCP and CLI — samgoodwin89 · 2026-11-21