What if the only thing you had to give an AI agent was an outcome and a budget?

That’s the future we’re headed for, according to Angela Jiang (@angjiang), head of product for the Claude platform: You give an agent a goal and a number, and it figures out the rest for you. The new Claude Managed Agents features, announced at this week’s Code with Claude developer event, are a step in this direction. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7.

Along with Angela, I chatted with Katelyn Lesse (@katelyn_lesse), head of engineering for the Claude platform, about what it takes to build an AI infrastructure platform on @every's AI & I.

If you found this episode interesting, please like, subscribe, comment, and share!

To hear more from Dan Shipper:

Subscribe to Every: https://every.to/subscribe

Follow him on X: https://twitter.com/danshipper

Timestamps:

00:01:48 - How the Claude platform evolved from API to agents

00:04:09 - The primitives that make up Claude Managed Agents

00:10:37 - Why the harness and the model are becoming a single unit

00:18:49 - The infrastructure wall that kills most agent projects in production

00:24:49 - Why team agents need a different shape than individual productivity tools

00:26:36 - How Anthropic's legal team uses an agent to review marketing copy

00:34:24 - Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms

00:35:50 - How to measure agent success with outcome and budget as the end state

00:39:11 - What the platform looks like a year from now, when Claude writes its own harness