Eval Driven Development
As AI agents move from prototypes to production, the traditional build-and-test mindset is no longer enough. Evaluation-driven development puts measurement at the center of the engineering loop, treating agent behavior as something to be continuously specified, tested, observed, and improved. We’ll look at how evals help teams catch regressions, compare model and prompt changes, and make better product decisions with evidence rather than intuition. Attendees will leave with a practical framework for building agents that are not just capable, but reliable, observable, and ready for real users.
October 22 — Conference Day
A seasoned Solutions Architect with over 20 years experience in the software industry, spanning 2 countries, Jyothi is passionate about software development and observability. When not sitting at her desk, she can be found hiking with her dog Pepper