Zero-Shot Learning

In this episode: Evals are becoming the new product development loop Feedback loops help teams learn from unpredictable AI behavior in production Traditional tracing tools don’t explain AI failures Choosing an LLM is more like choosing a database than a CPU The agent layer should be treated as disposable   Zero-Shot Learning is a builder-to-builder podcast about how AI systems are designed, deploy...

In this episode: Why AI agents can't be trusted users The hardest security decisions are about what not to protect Everything in security is a proxy, including agents Secure-by-default doesn't mean slowing productivity AI-generated code isn't vibe-coding if a human verifies the work Zero-Shot Learning is a builder-to-builder podcast about how AI systems are designed, deployed, and secured. Subscri...

In this episode: React has become the default framework for AI-generated code AI is closing the gap between product ideation and engineering execution The ability to securely run and isolate AI agents must be built into platforms What the return to full-stack thinking means for the future of software engineering Tools like v0 put production-grade app building in the hands of anyone with an idea  ...

In this episode: Old identity models weren’t built for agents The hardest security problems begin after access is granted Long-running agents expose the limits of OAuth Secrets remain one of the weakest links in agent design How to stop agent overreach in real time with short-lived credentials and runtime boundaries Zero-Shot Learning is a builder-to-builder podcast about how AI systems are design...