In the news
What's New in Managed Deep Agents: schedules, per-run configuration, and Slack reactions
LangChain · Published · 3 min read
In 30 seconds
- What happened
- LangChain released Managed Deep Agents v0.9 with agent-created schedules, per-run configuration, and Slack reaction acknowledgments.
- Why it matters
- Engineers building internal Slack agents or multi-team deployments need flexible scheduling, dynamic tool selection, and user feedback mechanisms.
- Watch out
- Per-run configuration requires runtime context handling; schedules execute with user permissions; reaction customization adds complexity to Slack integration.
- agent
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.