Season 2 · Episode 1926
How We Built a 2,000-Episode AI Podcast Engine
We pulled back the curtain on the tech stack behind our 1,858th episode. From Gemini to LangGraph, here’s how we automate quality.
My Weird Prompts · Daniel Rosehill
April 2, 202622m 31s
Audio is streamed directly from the publisher (dts.podtrac.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
Reaching nearly 2,000 episodes is a staggering milestone, but it raises a question: how do you maintain quality at that scale? In this special episode, we pull back the curtain on the entire evolution of our AI podcasting pipeline. We trace the journey from brittle, linear chains to a sophisticated agentic substrate powered by LangGraph, random model pools, and serverless GPU clusters. Discover how we moved past the "dancing bear" stage to build a system that generates a "Permanent Research Artifact" every single time, all while keeping costs negligible and creative freedom high.