In the news
How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents
LangChain · Published · 3 min read
In 30 seconds
- What happened
- LangChain released Schedules SDK for Managed Deep Agents, enabling proactive agents that run autonomously on cron schedules rather than waiting for user input.
- Why it matters
- Engineers building ambient AI agents need this when they want agents to perform background tasks like memory consolidation, proactive outreach, or monitoring without manual triggering.
- Watch out
- The approach relies on cron servers and agent-friendly interfaces; success depends on proper load distribution, permission governance, and clear scheduling semantics.
- agent
- sdk
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.