Agents are moving from tools you prompt to infrastructure that runs your business. But what does it take to run them in production?
Jess Yann (Product Manager, Claude Managed Agents), Katelyn Lesse (Head of Engineering, Claude Platform), and Angela Jiang (Head of Product, Claude Platform) discuss how teams are building agentic infrastructure, including identity, permissions, memory, and agent-to-agent communication. They also share how organizations should think about agentic ROI and designing human-agent teams that adapt to evolving model intelligence.
Learn more about the Claude Platform: https://claude.com/platform/api
0:00 Intro
1:00 - Building Claude Managed Agents in production
2:15 - How agents talk to each other
3:00 - The future of agentic infrastructure: thinner harnesses and adversarial agent pairs
8:20 - Barriers to agentic adoption: security, compliance, and evals
9:15 - How to measure agent ROI
12:45 - Failure modes: hyper independence and sprawl
13:30 - The future: agents as an invisible substrate
15:15 - What's next for the Claude Platform
