aiqbench analysis
This release extends AI agents to websites without APIs, using a managed browser that can persist logins per conversation or per user. The `browser_handoff` feature lets the agent pass control to a human at login or two-factor steps, so credentials stay out of model messages and traces. Readers building agents should note that the main gain is access to API-less sites, while the security and session-scoping details will determine whether it fits their use case.
Managed Deep Agents v0.10: Browser Use and Async Subagents
Managed Deep Agents v0.10 adds browser use, so agents can work on sites with no API and hand you the window to sign in, and async subagents for background work.
Managed Deep Agents v0.10 is out today. It adds browser use, so your agent can work on websites that have no API, and async subagents, which run long tasks in the background while your agent keeps talking to you. In this post, we cover why agents need each one and how to turn it on, then the rest of the release. Booking travel, canceling a subscription, or filing a claim all happen on sites built for people clicking through pages, and there's often no API an agent can call. While agents can reason through how to complete the task, they…
Excerpt shown under the publisher's RSS terms · 100 words · full text and figures are on the publisher's site
Related coverage
[Linkpost] Looking into the Swarm's Eye
LessWrong · Sep 26, 2026
A Beginner’s Guide to Setting Up Claude Code for High Performance Agentic Programming
KDnuggets · Jul 20, 2026
[AINews] Building AIE CODE: The top Coding Agent Conference
Latent Space · Oct 30, 2026
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
Latent Space · Sep 9, 2026