Hamel Husain & Shreya Shankar

Building systematic metrics allows teams to move beyond subjective 'vibe checks' and iterate on AI features with the same confidence as traditional software.

"Evals help you create metrics that you can use to measure how your application is doing and kind of give you a way to improve your application with confidence. That you have a feedback signal in which..."

Streamline the categorization of AI errors by appointing a single 'benevolent dictator' with domain expertise to define quality standards instead of relying on a committee.

"When you're doing this open coding, a lot of teams get bogged down in having a committee do this. For a lot of situations, that's wholly unnecessary. You don't want to make this process so expensive t..."