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
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.
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.
prompt injection — An attack that hides instructions in content an AI will read — a webpage, email, or document — tricking it into following the attacker instead of the user.
Why it matters
Restricting what an AI agentAn 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.Full definition → may fetch is one of the few practical defenses against prompt injectionAn attack that hides instructions in content an AI will read — a webpage, email, or document — tricking it into following the attacker instead of the user.Full definition → through retrieved content, and it is now a parameter rather than a wrapper you write.
postClaude Desktop now starts ~2x faster than it did a month ago.
postClaude Code can design now. The new /design skill (research preview) brings Clau
postPerf win of the day: Claude Code CLI now uses 2x less CPU at p99. Bun's garbage 
