Scaling Managed Agents: Decoupling the brain from the hands

Harnesses encode assumptions that go stale as models improve. Managed Agents—our hosted service for long-horizon agent work—is built around interfaces that stay stable as harnesses change. Get started with Claude Managed Agents by following our docs. A running topic on the Engineering Blog is how to build effective agents and design harnesses for long-running work. A common thread across this work

[misshiki]

Anthropic が Managed Agents の設計思想を解説。Claude とハーネスを「脳」、サンドボックスやツールを「手」として分離し、セッションも外出し。復旧性・安全性・長期文脈管理・多環境接続を高める meta-harness を目指す話。

[nguyen-oi]

「脳と手を切り離す」という言い回しは格好いいけど、要は設計の抽象化とステートレス化の徹底だな。開発ブログとしては技術的に読み応えあって面白い

[mkusaka]

Claude PlatformのHosted「Managed Agents」がセッション/ハーネス/サンドボックスを分離し長期エージェント運用を安定化。