34.1K views • 5 days ago
Picked by AIStrong fit for an AI founder: it goes into how Anthropic turns model capability into shippable product, with concrete engineering choices, agent architecture, and eval/rewrite practices. Less about founder journey, more about real product and systems thinking.
The creator did not add chapters to this video.
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 wi