An agent’s sandbox can die without taking the whole agent with it. That’s the idea behind “the brain and the hands,” Anthropic’s architecture for Claude Managed Agents. Now that the dust has settled on Opus 5.5, it is universally agreed to be the best model in the world. In this conversation with Katelyn Lesse and Angela Jiang, Anthropic’s Heads of Engineering and of Product, goes inside the systems that turn model capabilities into products developers can use. We cover: - Why Anthropic separated the agent harness, session state and execution environment. - Letting agents use credentials without putting those credentials inside their sandboxes. - Rebuilding the Messages API from Python to Rust with Claude-and verifying the rewrite with shadow traffic.
Working out what this means for your business?
Aileron Shift builds the systems behind this site: AI-written, human-reviewed publishing, marketing automation and WordPress hosting for companies that need to move faster than their competitors.