• Retrieval Didn't Die. It Grew Up
    Nov 11 2026

    Million-token context windows were supposed to make retrieval obsolete. The prediction keeps not coming true, and the reasons why are the design constraints of any knowledge architecture you'll build. This episode covers what good retrieval looks like now, the quiet breakthrough of fixing chunks instead of queries, and the genuinely new decision: should your code drive the search, or should the model?

    Show More Show Less
    9 mins
  • The Economics of Context
    Nov 11 2026

    Got something to say to this podcast? Send a voicemail, and you might hear yourself on the next episode!

    Model prices get the headlines, but architecture decides the bill. Two systems on the same model can differ in cost per request by a factor of fifty. This episode explains the unusual shape of language model pricing, then walks through the three levers that move cost and latency more than any model choice: prompt caching, routing, and context discipline. Plus the one dynamic value that silently makes your prompt cost ten times more.

    Show More Show Less
    9 mins
  • Approval is an Architecture
    Nov 11 2026

    Got something to say to this podcast? Send a voicemail, and you might hear yourself on the next episode!

    For a decade, "human in the loop" was a reassuring phrase on a slide. That era is over, because the machines now act, and US regulators have noticed. This episode walks through what FINRA, the banking supervisors and Treasury now expect of firms running agents, how the approval checkpoint is becoming standard protocol plumbing through MCP elicitation, and the subtle failure the protocol doesn't solve for you: proving that what executed is what the human actually approved.

    Show More Show Less
    9 mins
  • The Specialist Without the Headcount
    Nov 11 2026

    Got something to say to this podcast? Send a voicemail, and you might hear yourself on the next episode!

    Every new procedure arrives looking like a case for a new specialist agent. Skills are the industry's answer, and they arrived fast: Anthropic released the format in late 2025, opened it as a standard, and within weeks OpenAI, Microsoft and GitHub had adopted it. This episode explains what a skill actually is, how progressive disclosure makes expertise nearly free until it's needed, and why a skill gives you most of what a specialist agent promised without the second loop, the second context, or the network hop.

    Show More Show Less
    10 mins
  • MCP Without the Mystique
    Nov 11 2026

    Few acronyms have traveled from a vendor blog post to board-level slides as fast as MCP. Most of what firms believe about it is myth. This episode strips the Model Context Protocol back to what it actually is, plain plumbing with a network effect, busts the three myths that distort architecture decisions, and explains why the newest revision quietly removed the one complaint that was true.

    Show More Show Less
    10 mins
  • The End of Parsing
    Nov 11 2026

    Got something to say to this podcast? Send a voicemail, and you might hear yourself on the next episode!

    For their first few years, language models communicated in the one format no contract can bind: prose. Strict structured outputs change that at the decoding level, turning a text generator into a typed component. This episode explains how constrained decoding works, the one thing it can't promise you, and why a schema is what finally makes AI steps composable with everything else you run.

    Show More Show Less
    9 mins
  • The Decision Layer
    Nov 11 2026

    Everyone pictures language models generating text. The less famous half of the technology is judgment, and it's about to change where models belong in your architecture. This episode is about the Decisions API: a model that doesn't write anything, just picks from options you define, in about two hundred milliseconds, with calibrated probabilities you can govern. It competes with your rules engine, not your chatbot.

    Show More Show Less
    9 mins