Choosing the right AI model shouldn’t feel like roulette. We sit down with Kate Catlin, the product manager from GitHub. Kate shares how model strengths and explains how auto mode aims to pick the right model for the job so developers can focus on outcomes.

We dig into practical tactics that cut through hype: start with a golden dataset, run evaluations early, and keep refining with real user prompts once your AI is live. If you’re overwhelmed by weekly model releases, you’re not alone—Kate outlines how to compare new options  with  scoring and selective manual review. 

She also tackles the enterprise challenge: slow model approvals that leave teams on outdated systems. With a disciplined eval pipeline, organisations can safely adopt newer, faster, and often cheaper variants that deliver better results.

Text Us About the Show