Ravi Madabhushi details how existing infrastructure, designed for human users, fails AI agents, leading to issues like rate limits and over-permissioning. He argues for treating agents as first-class principals with fine-grained, context-aware authorization and robust visibility to prevent non-deterministic and potentially rogue behaviors.
Most AI agents lack a "save button" for persistent state, making debugging and optimization challenging. This talk introduces the concept of a durable runtime with checkpointing, allowing developers to replay agent executions, perform "what-if" analyses (e.g., swapping models, mocking tools), and conduct cohort-based evaluations using production data. The open-source tool Kitaru is demonstrated as a solution to build, debug, and improve agents at scale by capturing full execution state, not just traces.