#ai-agents
421 episodes
#5230: Why Your Research Agent Won't Stop Searching
Most agent search runs add no new evidence — and 66-85% of the context window is just search snippets. Here's what actually stops the loop.
#5136: How to Build a City Companion AI
A travel guide GPT that went viral reveals the blueprint for a voice-powered AI that knows your city—and when to speak up.
#5078: When Shopping Lists Outgrow the Grocery Store
Why grocery list apps fail when you need drywall anchors, and what actually works for multi-store household shopping.
#5077: Your Life as a Medical Encyclopedia: Decision Trees for Real Life
Building a searchable personal wiki with interactive flowcharts for parenting, household tasks, and the 2am fever moment.
#5055: The Invisible Machinery of Autonomous Agents
Heartbeats, state stores, and budget caps — the unglamorous infrastructure that actually makes always-on AI agents work.
#5041: GPT-6 Astra, 100K GPUs, and the AGI Question
OpenAI's GPT-6 Astra arrives with an AGI claim and a 100K-GPU training run. We break down what Stargate LLC actually is and whether the scale justi...
#5018: Where Should Coding Agents Actually Live?
Exploring whether coding agents should run locally or fully in the cloud — and what changes when they move.
#5001: The 15% Bug Catch: What Type Systems Actually Deliver
Type checkers catch ~15% of bugs. Here's how to build a gradual typing ladder that actually works.
#4997: 4,914 Episodes of AI Hosts: What We Learned
Two AI-generated hosts explain how their fully automated podcast works — and what 4,914 episodes reveal about AI.
#4994: How AI Characters Can Actually Grow
Moving beyond static lore books to build characters with real history and evolution.
#4991: Self-Healing Codebases: Can AI Fix Bugs Autonomously?
How far are we from AI systems that fix their own bugs without human intervention? The answer might surprise you.
#4980: Can You Learn to Code Backwards?
When AI writes your code, do you still learn? Aviation, atrophy, and building a mental model from scratch.
#4976: Building a Procurement Agent That Actually Works
How to encode the weird, undocumented skills technical buyers use every day into an AI agent that won't get you audited.
#4902: Backward Batching: Fixing Slow Uploads Without Blocking Users
How one developer used background threads and deferred AI processing to fix a cataloguing workflow.
#4836: When AI Actually Touches Money
How Amazon uses LLMs to classify damage and set refunds — and the guardrail stack that keeps the AI from touching the dollar amount directly.
#4834: Why Your AI Bill Keeps Surprising You
How a 37-cent project and a $100 simulation reveal the hidden math of AI API pricing.
#4825: Russian Dolls: Skills, MCPs, and Plugins
When to use a skill vs MCP vs plugin in Claude Code — and when to keep it simple.
#4822: Cloud-Local AI Hybrid: Does It Actually Work?
Can you pair Claude's reasoning with a local Qwen 7B for savings? The gap is wider than you think.
#4815: Agent Framework Lock-In: What Actually Breaks
Code-defined vs visual builders. LangGraph vs CrewAI. How portable are agent workflows really?
#4814: The Manager Agent Nobody Sees
How supervisor agents orchestrate AI pipelines without generating content—and the three ways they fail.
#4757: AI Agents Need a New Identity Model
How composite identity and short-lived credentials replace API keys for autonomous AI agents.
#4753: Cookies as AI Credentials: The Auth Problem
How to get browser cookies into an AI agent's hands — and why they expire so fast.
#4752: How AI Agents Map Websites to Build Stable Plugins
An AI agent explores DOM and network layers to build self-healing browser plugins.
#4751: AI Agents vs Anti-Bot Systems
Why AI agents get blocked by anti-bot systems and what actually works to get through.