EPISODE 27Ankur Goyal joins Founder Mode to show how real teams get from AI prototype to production: build a two-click loop from user complaint to eval, treat observability as a driver of quality, and design iteration environments that connect production logs back to tests. Ankur explains why LLMs behave more like databases than CPUs, how to avoid eval fatigue by curating the 5–10 examples that matter, and why top teams re-evaluate model choices monthly. He also looks ahead to agents that can review and improve other models’ work, turning today’s manual feedback loops into scalable systems.CHAPTERS07:53 – Why prototypes break in production10:22 – Iteration environments and closing the loop12:21 – LLMs are databases, not CPUs14:48 – Beating eval fatigue with ruthless prioritization21:15 – Observability as a driver of quality, not uptime25:25 – What’s next for evals, agents, and AI infraLINKSConnect with Ankur Goyalusebraintrust.com • LinkedIn • X/TwitterSPECIAL OFFEREmail [email protected] and mention Founder Mode to receive a special offer.Stay Connected with Founder ModeSubscribe to our newsletter: foundermode.kit.comConnect with KevinLinkedIn • X/TwitterConnect with JasonLinkedIn • X/Twitter

Ver todos los episodios