Scaling Managed Agents: Decoupling the brain from the hands
- Source
- anthropic.com
- Author
- Anthropic Engineering
- Date
Understanding how Anthropic decouples the model, execution environment, and session state into swappable interfaces gives you a concrete blueprint for building infrastructure that survives model and upgrades without rearchitecting your system.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
- sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
- 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.
“Harnesses encode assumptions that go stale as models improve.”
“But when we used the same harness on Claude Opus 4.5, we found that the behavior was gone. The resets had become dead weight.”
“In our case, the server became that pet; if a container failed, the session was lost.”
“The solution we arrived at was to decouple what we thought of as the “brain” (Claude and its harness) from both the “hands” (sandboxes and tools that perform actions) and the “session” (the log of session events).”
Checking sign-in…
Loading comments…