AI · Official
LangChain Shows How to Build Always-On Proactive Agents With Scheduled Tasks
LangChain blog ·

At a glance
LangChain published a guide on building proactive agents that act on their own, using cron-style schedules. The post says these schedules power features like memory consolidation, proactive messages, and reminders. It also says many emerging proactive agents are built on this simple pattern.
Key points
- Proactive agents often run as scheduled cron tasks instead of waiting for a user to type.
- Scheduled jobs can consolidate past conversations into long-term memory.
- Agents can send proactive messages toward a goal, check event streams, set reminders, and manage other agents.
- Building these agents needs a reliable cron server that lets developers set schedules and prompts.
Why it matters
It explains how always-on AI assistants can act without being asked, which shapes how future AI tools will behave.
Original source
How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents
LangChain blog · Nov 18, 04:55 KST
Read on LangChain blog ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to LangChain blog.
More from this field
- AWS Agent Registry Adds Custom Metadata Schemas for Governing and Finding Records
AWS has added custom metadata schemas to AWS Agent Registry. Administrators can define shared fields, such as environment or owner team, and every record in the registry must follow them.
Amazon AWS Machine Learning blog · Nov 18, 05:31 KST - AWS Shows Three Secure OAuth Setups for Snowflake Cortex AI Agents
Amazon's AWS team wrote a guide on connecting AI agents to Snowflake's MCP server with secure login tokens. It compares three OAuth setups that control which user or service is allowed to call Snowflake's AI tools.
Amazon AWS Machine Learning blog · Nov 18, 05:25 KST - OpenAI Engineers Show How They Work with Codex Agents in Daily Projects
This talk shows how OpenAI engineers Dominik Kundel and Charlie Guo use Codex, OpenAI's coding agent, in everyday work. It was given at the AI Engineer event, and the video is based on a CODE Summit 2026 session.
AI Engineer · Nov 18, 04:43 KST