Framework
Personalization as the North Star
The current AI DJ surfaces the same highlights for all users. The roadmap moves toward a fully personalized agent.
How it works
- 1The agent will learn what you save, what you replay, and what you skip.
- 2Users will eventually prompt the DJ in natural language: 'Always include book recommendations from Lenny' or 'Find me everything about hiring from the last 30 days.'
- 3Personalization creates compounding returns — the longer you use it, the more precisely it matches your learning style.
Hear it on the podcast
Podcast DJ: The Cliff Notes for Your Podcast QueueListen to the episodeMore from this episode
The Signal-to-Noise Problem in Content ConsumptionMost podcast content is context-setting, banter, or setup. The insight-dense moments are a fraction of total runtime.The Highlight Reel ModelKevin draws the analogy to sports: you watch the big match in full, but for the other 10 games you want highlights.The Hive Brain AdvantageSnipd is the only podcast app with data on which specific moments inside an episode users found valuable.Content Creator vs. Listener ControlTools like Opus Clip give creators control over which moments get amplified. Kevin argues the future flips this.
Get the next framework first
One email a week with the frameworks, tools, and founder stories from the podcast. Free.
More frameworks for AI & Automation
The Three Categories of HallucinationDevansh breaks legal AI hallucinations into three categories. The third is the most dangerous, and the hardest to catch with traditional vector search.The Round Table of Second OpinionsInstead of marrying one model, poll all of them. Each model has different training data, different personality, different blind spots.The Unidentified Data PrincipleMost apps say encrypted, in transit, at rest, de-identified. Stephen goes one step further with an architecture where the business model physically cannot pivot into data harvesting.The LLM-as-Wireframe MethodDavid's practical framework for using AI responsibly in legal contexts without replacing professional counsel entirely.Deterministic Logic Plus Conversational AIMost online will builders are wizard-based forms. You fill in fields, answer dropdowns, and a document gets generated. The problem is that approach assumes you already know what you want. That's almost never true. Succession Wills solves this with a split architecture.Build for Signal, Not AssumptionWhen training models for human behavior, go in with as few assumptions as possible. Let the data surface the features. Your intuitions about what matters are often wrong.