Claude Managed Agents get sandbox memory, domain controls, and a session viewer
- Source
- x.com
- Date
We shipped three updates to Claude Managed Agents. First, we made it easier to use memory with Self-Hosted Sandboxes. Any work done in a Self-Hosted Sandbox can be saved to memory.
Second, we've added domain controls. web_search and web_fetch now take allowed_domains or blocked_domains, so you can control what the agent is allowed to search and read.
Finally, we've redesigned the Console session viewer for multi-agent sessions. It now has a minimap with one lane per agent, a streaming transcript grouped by agent iteration, and an inspector with cost in dollars per thread and per session. Live now: https://t.co/0uq2eZXau6
Context
Anthropic added domain restrictions to the web tools in Claude Managed Agents. Developers can supply allowed domains or blocked domains to web_search and web_fetch, specifying where those tools may search or retrieve pages. The announcement and its code example show the restrictions attached to individual tools, allowing search and page retrieval to use different policies.
This gives developers a concrete control over the sources an consults through those tools. Its scope is web search and retrieval; the announced settings do not establish a network-wide restriction on every action an agent might take.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
- multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
Checking sign-in…
Loading comments…