Systems | Development | Analytics | API | Testing

Rick Kranz has built over 100 AI automations for his community and clients — he has no reason to defend Databox. But when he tried to run his AI analysis without the Databox MCP, it just stopped working. In this episode, Rick and Pete break down exactly why: the semantic layer, the metric definitions, and the standardized math that make an AI's answer trustworthy instead of a guess. If you've ever wondered why connecting five random MCP servers to Claude doesn't give you the same results as a purpose-built data layer, this is the episode.

Quick application integrity check: can your quality strategy survive the tsunami of code coming its way? AI is accelerating development, increasing code abstraction, and multiplying the volume of software teams need to validate. But existing QA approaches weren't built for this level of speed and scale. Application integrity closes the growing gap between what teams build and what they can verify, providing continuous assurance that software works as intended.

Drawing on his experience at Google, Google X, and as the CEO and co-founder of an AI startup, Varun Puri shares practical lessons on embedding AI into everyday workflows and building habits that stick. Discover how to maintain perspective on what is working, even when AI constantly highlights what isn’t.