Managed Deep Agents v0.10 adds browser use and async subagents
Managed Deep Agents v0.10 adds browser use and asynchronous subagents. Browser tools let agents work with websites that lack APIs, while thread- and user-scoped sessions manage browser state. Browser handoff lets people complete sign-in or two-factor prompts themselves, keeping passwords out of model messages and traces. Async subagents can run long tasks in the background while the main agent continues its conversation; users can check, update or cancel those tasks. The release also adds thread-origin records, run-stopping controls, experimental Slack channel handlers and resolveUser support.
The release lets agents handle website-based tasks without APIs and run long jobs without blocking the main conversation, while human handoff allows people to authenticate without exposing credentials to the agent.
Key Takeaways
- A browser lets agents do work on the web that APIs can't cover, including clicking, scrolling, and filling out forms.
- Managed Deep Agents now runs a browser for your agent, with tools tuned for context-efficient browser use.
- Managed Deep Agents ships with support for thread and user scoped browser sessions. Handoffs allow users to log into and interact with websites with credentials persisted across sessions.
Agents have gotten good enough to work where we work, and a lot of that work happens in a browser. Booking travel, canceling a subscription, or filing a claim all happen on sites built for people clicking through pages, including ones the agent didn't plan to visit. Often there's no API an agent can call. Fetching the page with curl doesn't get far either, since it returns the HTML before any JavaScript renders the page and can't click anything.
Personal agents like Instinct and Meta's Muse already work this way. Browser agent traffic is growing fast too, and DataDome saw agentic browser requests jump 4.7x in September alone.
Managed Deep Agents lets you build and deploy agents in LangSmith without running any infrastructure. You write the agent's instructions and tools, and LangSmith runs the harness and runtime. Today, we're giving these agents a browser, so you can build your own agents that work on the web. Managed Deep Agents runs the browser too, and gives your agent tools tuned for it.
#LangChain#Managed Deep Agents v0.10#LangSmith#Stagehand#Browserbase#Slack