LangChain outlines managed deep agents with durable workflows, sandboxes, and observability
Overview
LangChain's Harrison Chase posts a summary slide on X describing the future of managed deep agents.
He says the slide aligns with LangChain's vision and lists durable workflows built on LangGraph and LangSmith Deployment, computer use through LangSmith Sandboxes, memory and skills through LangSmith Context Hub, schedules, connectors, text and voice channels, and evals. Chase says payments and identity are the only missing pieces. The post is a statement of direction from Chase, not a product release with dates, prices, or availability.
Written by AI from the articles below · updated Oct 11, 11:50 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
Harrison Chase@hwchase17XLangChain outlines managed deep agents with durable workflows, sandboxes, and observabilityAIHarrison Chase says his summary slide shows how future agents will look and that it aligns with LangChain's managed deep agents vision. The slide lists durable workflows built on LangGraph and LangSmith Deployment, computer use through LangSmith Sandboxes, memory and skills through LangSmith Context Hub, schedules, connectors, text and voice channels, and evals. He says payments and identity are the only missing piece.

Heat trend
- Current comparable heat
- 9
- Peak comparable heat
- 10Oct 11, 12:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.