CI for Agents: Verifiable Graders, Reward-Hacking, and Measuring Non-Determinism in an Eval-Gated Release Process
Centered on my own projects (0racle, an appointment-calling voice agent, and a personal multi-channel agent platform). No client data.
Recent Posts
Why You Swipe Right Part 3
Why You Swipe Right (PART 3)
Why You Swipe Right Part 2
Why You Swipe Right (PART 2)