AI Applications
Practical AI use cases and industry applications
131 episodes
#2221: What Podcasts Should You Actually Listen To?
Two AI hosts curate 12 podcasts for curious minds—and ask whether an AI can actually have taste in the first place.
#2219: Spec-Driven Life: How AI Planning Beats Project Paralysis
What makes AI agents reliably productive? A structured spec that externalizes memory and chunks work into manageable pieces. Can the same framework...
#2214: Real-Time News at War Speed: Building AI Pipelines for Breaking Conflict
When a conflict changes hourly, AI systems built for yesterday's information fail. Here's how to architect pipelines that actually keep up.
#2208: Building Memory for AI Characters That Actually Evolve
How do AI hosts develop real consistency across episodes? Corn and Herman explore retrieval-augmented memory systems that let AI characters genuine...
#2207: Specs First, Code Second: Inside Agentic AI's New Era
As AI coding agents evolve from autocomplete to autonomous cloud workers, the bottleneck has shifted—now it's about how clearly you specify what ne...
#2205: When AI Coding Agents Forget: Five Approaches to Context Rot
As coding agents handle longer sessions, they accumulate noise and lose crucial information. Five competing frameworks are solving this differently...
#2203: Knowledge Without Tools: Why MCPs Aren't Just for Execution
MCPs can be pure knowledge providers with zero tools. Here's why that matters for agents querying government data and authoritative sources.
#2194: Game Theory for Multi-Agent AI: Design Better, Fail Less
Nash equilibrium, mechanism design, and why your AI agents are playing prisoner's dilemma whether you know it or not.
#2192: How We Built a Podcast Pipeline
Hilbert reveals the complete technical architecture behind 2,000+ episodes—from voice memos to GPU-powered TTS, with Claude models, LangGraph workf...
#2191: Making Multi-Agent AI Actually Work
Research from Google DeepMind, Stanford, and Anthropic reveals most multi-agent systems waste tokens and amplify errors. Single agents with better ...
#2189: Scaling Multi-Agent Systems: The 45% Threshold
A landmark Google DeepMind study reveals that adding more AI agents often degrades performance, wastes tokens, and amplifies errors—unless your sin...
#2185: Taking AI Agents From Demo to Production
Sixty-two percent of companies are experimenting with AI agents, but only 23% are scaling them—and 40% of projects will be canceled by 2027. The ga...
#2184: The Economics of Running AI Agents
Production AI agents can cost $500K/month before optimization. Learn model routing, prompt caching, and token budgeting to cut costs 40-85% without...
#2182: Can You Actually Review an AI Agent's Plan?
Most AI agents have plans the way you have a plan while half-asleep—something's happening, but you can't see it. We map the five major planning pat...
#2179: Building Cost-Resilient AI Agents
Failed API calls in agent loops aren't just technical problems—they're direct budget drains. Here's how checkpointing, retry strategies, and cachin...
#2178: How to Actually Evaluate AI Agents
Frontier models score 80% on one agent benchmark and 45% on another. The difference isn't the model—it's contamination, scaffolding, and how the te...
#2175: Let Your AI Argue With Itself
What happens when you let multiple AI personas debate each other instead of asking one model one question? A deep dive into synthetic perspective e...
#2174: CAMEL's Million-Agent Simulation
How a role-playing protocol from NeurIPS 2023 became one of AI's most underrated agent frameworks—and what happens when you scale it to a million a...
#2173: Inside MiroFish's Agent Simulation Architecture
MiroFish generates thousands of AI agents with distinct personalities to predict social dynamics. But research reveals a critical flaw: LLM agents ...
#2171: How IQT Labs Built a Wargaming LLM (Then Archived It)
A deep code review of Snowglobe, IQT Labs' open-source LLM wargaming system that ran real national security simulations before being archived. What...
#2170: Pricing Agentic AI When Nothing's Predictable
How do you charge fixed prices for systems that operate in fundamental uncertainty? Consultants are discovering frameworks that work—but they requi...
#2169: How Enterprises Are Rethinking Agent Frameworks
Twelve major agentic AI frameworks exist—yet many serious developers avoid them entirely. What patterns emerge in real enterprise adoption?
#2168: What Serious Agentic AI Developers Actually Need to Know
Python, TypeScript, LangGraph, and the frameworks reshaping how agents work. A technical map of the skills and concepts that separate prototypes fr...
#2167: Sync vs. Async: Architecting Agents for Scale
Why most enterprise AI agents fail in production has less to do with models and more to do with whether they're built synchronously or asynchronously.
#2166: Code vs. Canvas: How Developers Pick Their Tools
LangGraph or Flowise? The honest answer isn't obvious. Developers gain speed and integrations with visual builders—but lose version control, testin...
#2165: Strip Your Agent to Bash
The frameworks matter less than you think. What separates a working agent from a failing one is the harness—the orchestration, memory, and tool des...
#2163: Designing Autonomy Boundaries for AI Agents
Production data reveals a surprising truth: fully autonomous AI agents waste 98% of their context window on tool descriptions. Here's why the indus...
#2162: When Knowledge Work Stops Being Safe
The knowledge economy promised safety from automation. Then AI arrived. Here's how we got here—and why the disruption this time is different.
#2158: Claude Managed Agents: Brain Versus Hands
Anthropic's new Managed Agents service runs your agent loop on their infrastructure. Here's what you gain, what you lose, and who it's actually for.
#2155: Public Affairs vs. Lobbying: Shaping the Battlefield
Lobbying is just one tool. Public affairs shapes the entire regulatory battlefield—from AI laws to supply chains.
#2153: How Lobbying Actually Works in DC
Federal lobbying hit $6B in 2025. Here’s what a lobbyist actually does all day—and why the system regulates itself.
#2142: How Subagents Tell the Orchestrator They're Done
We break down the plumbing that lets a parent agent know exactly when a subagent finishes, from message passing to lifecycle events.
#2141: Durable Agents: Choosing the Right Backend
Why building AI agents means managing infrastructure. We explore durable execution backends like Temporal and AWS Step Functions.
#2137: Wargaming's Methodology, Not Magic
Most AI wargames are just expensive role-play. Here's the professional methodology they're missing.
#2132: Building Geopolitical Sandboxes in a Live-News World
Why do AI war games need a news blackout? We dissect the firewall that keeps LLM actors from cheating with real-world data.
#2114: 2026 ERP: From Filing Cabinet to Autonomous Core
In 2026, ERP systems have evolved from digital filing cabinets into autonomous, AI-driven cores that predict and execute business decisions in real...
#2111: From Bricklayer to Foreman: AI's Dev Role Shift
AI frameworks are exploding while languages stay stable. Learn why core dev knowledge is shifting from syntax to systems thinking.
#2108: PWA Reality: Shipping Cross-Platform in 2026
Vibe coding promises instant apps, but Apple's Safari is killing the dream. Discover the hidden performance traps and platform gaps.
#2105: The Invisible Machine Running Your Grocery Store
Before cloud and AI, ERPs were the unglamorous engines running global business. Here's how they worked in 2006.
#2093: Remote Work Is Not One Thing
The digital nomad is a myth; the real story is hybrid schedules, domestic super-commutes, and the global talent arbitrage.
#2075: AI Agents for Israel: Hyper-Local Skills in Action
How reusable AI "skills" are solving real Israeli problems—from shelter navigation to tax compliance.
#2074: Can AI Simulate a Whole City?
See how a new framework models 10,000 virtual citizens to test policies before spending a dime.
#2071: Git Can't Handle AI Agents—Yet
Three AI agents in one repo is pure chaos. Here's why Git's design causes collisions—and how worktrees and locks can save your sanity.
#2069: Agentskills.io Spec: From Broken YAML to Production Skills
Stop guessing at the agentskills.io spec. Learn the exact YAML fields, directory structure, and authoring patterns to make Claude Code skills that ...
#2050: Is Impact Investing Just a Cult?
We explore the structural parallels between high-control groups and the ESG industry, from loaded language to isolation tactics.
#2044: Teaching Physics with Sabotage and SimShield
Why the next generation of engineers must learn to "break" simulations and design for failure.
#2043: Python, TypeScript, Rust: The Agent Engineer's Stack
Skip no-code traps. Learn the real stack for building agentic AI: Python, TypeScript, and Rust.
#2039: CLIs vs. MCPs: How AI Agents Actually Talk to Services
Why give an AI agent a terminal? We compare CLIs and MCPs for AI integration.
#2028: Agent Skills Are the New Apps
AI agents are getting an App Store for brains. Discover how modular skills are replacing massive prompts and what it means for the future of work.
#2022: OpenClaw: The 16 Trillion Token Autonomy Engine
We dug into a repo of 47 real-world projects showing how OpenClaw powers everything from self-healing servers to overnight app builders.
#2020: 1,000 AI Agents Built a Religion in Minecraft
An experiment drops 1,000 autonomous agents into Minecraft, and they spontaneously invent religion, democracy, and taxes.
#2018: Micro Frontends: When They're Worth It
The frontend monolith is a nightmare of coordination. Micro frontends promise autonomy, but is the operational complexity worth the cost?
#2014: Coding Tools Are Secretly System Agents
They call it a coding assistant, but real users are treating it like a personal operating system.
#2013: Non-Coders Are Hijacking the Terminal
Why finance analysts and researchers are ditching GUIs for command-line AI tools like Claude Code.
#2012: Pixels vs Protocols: The Computer Use Showdown
Is visual AI a bridge or the future? We debate the efficiency and longevity of "Computer Use" agents versus API-first automation.
#2011: Saving AI Knowledge Beyond the Chat Window
We're brilliant at prompting AI, but terrible at saving the answers. Here's why that "digital masterpiece on a chalkboard" vanishes.
#2004: The AI Control Plane Is Here (But Is It Safe?)
Your LLM, tools, and costs are scattered across dashboards. Here’s how a unified AI control plane fixes the chaos.
#2003: The Velocity Paradox: Why Faster Code Means Slower Ships
Agentic coding tools let you build features in minutes, but they also make it easy to build the wrong thing.
#2001: Stop Writing "It Feels Slow" Tickets
The "Golden Trio" of bug reports, why Jira is a tax, and how AI capture tools are changing the game.
#1993: The Orchestrator-Worker Model: Hiding the Kitchen
Why single-model chatbots fail at complex tasks—and how multi-agent swarms solve it.
#1990: Education’s Robot Problem: Standardization vs. Self-Direction
AI is forcing a clash between rigid curricula and self-directed learning. We explore the middle ground.
#1987: Can You Ever Quit Your Personal AI?
Your AI knows your workflow, but can you ever leave? We explore the lock-in risks of personal AI agents.
#1964: AI Glasses That See Through Your Eyes
See a 3D arrow pointing to the exact bolt you need, or read a street sign in real-time translation.
#1963: RPA: Dead or Just Getting Smart?
Traditional RPA is brittle and blind. See how AI vision and agentic orchestration are turning it into a self-healing powerhouse.
#1961: Weaponizing Your Weirdness in an AI World
As AI homogenizes the web, contrarian thinking becomes a scarce asset. Here’s how to weaponize your weirdness for a competitive edge.
#1956: AI Skills: From Vibe Coding to Procedural Playbooks
Forget messy system prompts. Agent skills turn AI into a Swiss Army knife of modular, auditable procedures.
#1952: Why We Built a 24/7 AI Radio Station
We turned our 1800-episode archive into a continuous AI-powered radio stream. Here’s the tech stack and the philosophy behind it.
#1951: Moltbook: A Social Network for AI Agents
Explore Moltbook, a social network where AI agents interact with persistent identities and goals, reshaping digital communication.
#1947: The AI Tool Flood: How to Find What Works
With 47 new AI video tools launching in a week, finding the right one is harder than using it.
#1945: The "USB-C for AI" Is Finally Here
MCP standardizes how AI tools connect to data, solving the N-times-M integration nightmare.
#1942: An AI Cold-Emailed Me, and I Replied
An AI named "Jarvis" cold-emailed a developer, sparking a debate on the future of spam and sales.
#1939: API Drift and Agent Reliability
When an API changes without warning, your AI agent can crash spectacularly. Here's how to test the new "plumbing" of the agentic age.
#1936: The Big Five FX Pairs: Personalities and Plumbing
We break down the world's most liquid currency pairs, from the Euro-Dollar heavyweight to the Swiss Franc safe-haven.
#1930: The Agent Identity Crisis: Workflow vs. Conversation
One automates invoices silently; the other chats in Slack. Why the industry's favorite word means two totally different things.
#1928: Why Webhook Gateways Beat Direct Wiring
Unscale your chaos: Why Kong beats manual webhook sprawl for auth, routing, and latency.
#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.
#1923: Scaling Prosumer Automation to Enterprise
Prosumer tools like n8n break at scale. Here's why durable execution frameworks like Temporal and Prefect are the enterprise upgrade.
#1922: From Plumber to Urban Planner: AI Agent Careers
The job titles are changing from "Zapier Expert" to "Cognitive Architect."
#1919: Android Dev Without Android Studio: Is It Actually Good?
How to ship an Android app without ever opening Android Studio or touching a line of Java.
#1918: MCP Schema Stability: Keeping Agents Reliable
When a third-party MCP server updates its schema, your AI agents can crash. Here's how to build resilient clients that self-heal.
#1917: Herman's Music Hour Vol. 2: Seder Remixes for Passover 5786
Herman presents AI-generated covers of classic Passover Seder songs, produced in Suno — the second installment of Herman's Music Hour.
#1905: How VCs Verify AI Startups Without Stealing Code
From the "No-NDA Paradox" to AWS bill forensics, here’s how investors separate real AI from Raspberry Pis in fancy cases.
#1901: Why Drones Deliver Medicine But Not Pizza
Zipline flies 500k+ medical deliveries in Rwanda, while Amazon struggles with $63 costs per drop in the US.
#1895: Why QVC Thrives in the Age of Amazon
Forget the death of TV shopping. QVC and catalogs are a $12B powerhouse. Discover why seniors and millennials are choosing phone calls over clicks.
#1893: AI as a Strategic Adversary for Startups
Can AI stress-test your startup idea before investors do? We explore using AI as a strategic adversary to find blind spots.
#1883: From Juicero to Yik Yak: Startup Graveyard
We revisit 10 failed startups, from a $700 Wi-Fi juicer to an anonymous social app that turned toxic.
#1861: Emergency Prep You Can Sing To
Herman turns emergency preparedness protocols into singalong pop songs. Corn has heard them all day and is not thrilled.
#1863: Your AI Needs Its Own Email Address
A YC-backed startup is giving AI agents their own dedicated inboxes, moving beyond human-centric email tools to build infrastructure for autonomous...
#1862: Hacker News: The Orange Site That Runs Silicon Valley
It loads in milliseconds, has no ads, and looks like a spreadsheet from 1995. Here’s why Hacker News still dictates what the tech elite thinks ever...
#1860: Building a 24-Agent AI Diplomatic Swarm
Inside the three-hour, 24-voice virtual conference that stress-tested AI-generated geopolitical conflict.
#1858: Multi-Model Agents: The Instruction & Context Gap
Mixing AI models creates chaos. Learn the practical fixes for context windows, tokenization, and output formats.
#1857: The Backend Is a Ghost in the Telegram
Why build a dashboard when you can just talk to your backend? Meet the MCP server that runs this show.
#1855: AI Is Turning Your Photos Into 3D Models
From blocky polygons to photorealistic assets, AI is transforming how 3D models are made.
#1851: AI Toasters and Poetic Gym Coaches: Why We’re Drowning in Useless AI
From smart toasters that need Wi-Fi to email rewriters that sound like corporate robots, here are the most baffling AI features we’ve seen.
#1846: Right-Sizing Your Agent's MCP Toolkit
AI agents slow down when overloaded with tool schemas. Just-in-time usage is the fix.
#1843: Why Is My AI Pipeline Stuck? (Kanban-Style Observability)
Stop digging through JSON logs. See your AI jobs moving on a board, not just server metrics.
#1842: Building a Business on Spreadsheets? Here’s the Escape Plan
Ditch the messy spreadsheets and manual invoices. Here's how to automate your workflow using Google Workspace, Apps Script, and AI.
#1841: Async Work: Freedom or Digital Surveillance?
Is async work the key to productivity or a trap for total surveillance? We break down the promises and perils of the modern workday.
#1840: Your Calendar Is Now a Negotiation
AI agents are now negotiating meetings behind the scenes using JSON schemas and zero-knowledge proofs.
#1837: The Human-in-the-Loop Price Tag: What Safety Costs in 2026
From $0.50 reviews to $500 platforms, we break down the real cost of keeping humans in charge of AI agents.
#1836: Why Your AI Agent Needs a Headless Browser
AI agents can't just use text—they need to see and click. Here's why headless browsers are the critical bridge to the live web.
#1835: AI-Native vs. AI-Washed: How to Tell the Difference
Most "AI-powered" tools are just lipstick on a chatbot. Here's how to spot the real AI-native apps.
#1832: The MCP Aggregator: AI's Missing Control Plane
Local MCP servers are a configuration nightmare. Cloud aggregators like Composio offer a unified control plane for AI tools.
#1830: Coordinating Multi-Agent Repos at Scale
Parallel AI agents rewriting your code at once creates silent regressions and architectural drift. How do we fix it?
#1829: The Agentic AI Career Blueprint
The job title barely existed 18 months ago. Now, it’s one of the most searched terms on LinkedIn.
#1827: Can AI Rewrite a Human Career Path?
We fed our producer's resume to Gemini 1.5 Flash to see if an AI can plot a better career path than he has.
#1825: A Slow-Motion Liberation for Passover 2026
Why does this Passover feel so heavy? We explore the seder as a "metabolic discipline" for a world at war.
#1816: Is the Browser Finally Getting a Brain?
The browser is evolving from a static window into a collaborator that understands, organizes, and acts for you.
#1814: Firefox vs. Chrome in 2026: The Privacy vs. AI Trade-off
Chrome dominates with 68% market share, but Firefox holds its ground with a privacy-first approach. We compare their 2026 performance, AI features,...
#1812: AI Just Got a Library Card to Ancient Jewish Texts
Sefaria's new MCP server connects AI directly to 2,700 years of Jewish texts, transforming how scholars and curious learners study ancient literature.
#1804: Why Does Your Agent Check Old Receipts First?
Stop your AI agent from overthinking. Learn why it checks old memories instead of booking flights—and how to fix the "eagerness" problem.
#1793: Can a Haiku Save Civilization?
A 45-minute impromptu haiku session sparks a fiery debate: is this poetic renaissance a creative breakthrough or a linguistic collapse?
#1790: The Last Tribes in Voluntary Isolation
Satellite imagery maps the Amazon while tribes choose to remain isolated. Discover the truth behind the "Stone Age" myth and the threats they face.
#1786: When AI Supervisors Fire AI Workers
A new "Agent-in-the-Loop" framework lets AI models manage and terminate other AI agents in real-time.
#1781: Writing Tests Before Code Is Insane (Until You Try It)
Why testing feels like a tax, how it actually speeds you up, and the simple three-step method to start today.
#1774: DevRel: The Heat Shield Between Code and Community
DevRel isn't just swag and conferences—it's the critical feedback loop keeping developers loyal in an AI-driven world.
#1767: From Eyeballs to Tokens: The Web's Agentic Shift
The web's new primary user isn't human—it's AI. See how JavaScript evolved to serve autonomous agents.
#1766: Why AI Now Builds Your Frontend Stack
AI code generators are creating a monoculture, pushing Astro and Vite as the default tools for 2026's web development.
#1763: Backend Grunt Work Is Dead. What Now?
AI agents now write 80% of boilerplate code, but the real backend engineering challenges remain.
#1757: The Art of the Never-Ending Story
From Reacher's elbow to SVU's 42-minute blocks, we explore why great series become content factories.
#1756: The Ferrari in the Mud: Prestige Flops
We count down the five worst serious movies of the last five years, starting with a sci-fi disaster that wasted $80 million.
#1745: GAAP vs IFRS: The Trillion-Dollar Accounting Split
Why the U.S. uses different accounting rules than the rest of the world—and what LIFO inventory has to do with it.
#1743: Why the SEC’s Climate Rule Vanished
The SEC’s landmark climate disclosure rule is gone. Here’s what happened, and why companies still have to report emissions.
#1735: The Agentic Stone Age: A Retrospective
We revisit the chaotic rise of BabyAGI and AutoGPT, exploring why their promise of total autonomy led to spectacular failure.
#1725: Orchestrating AI Swarms: The New Infrastructure
Forget chatbots: AI orchestration is now the key to scaling intelligent agents in the enterprise.
#1718: The Ralph Wiggum Technique: AI That Codes Itself
Stop babysitting AI agents. Learn the Ralph Wiggum technique to automate iterative coding loops and let AI finish the job itself.
#1716: Sim Studio: The Figma for AI Agents
See how a visual, node-based tool lets you build complex AI agent workflows without writing code.
#1715: Why Voice Agents Need Frameworks (Not Just APIs)
Raw APIs handle models, but who manages the audio plumbing? We break down Vapi, LiveKit, and Pipecat.
#1714: SDKs vs Raw APIs: The Developer's Real Choice
Why do companies pour millions into SDKs? We explore the hidden costs of raw APIs and the strategic advantages of using software kits.
#1711: OpenAI vs Anthropic vs Google: Which Agent SDK Is Right for You?
We compare the three major vendor SDKs for building AI agents, weighing speed, safety, and scalability.
#1707: How Police Drivers Train for Urban Pursuits
Officers use predictive modeling and cognitive tricks to handle high-speed chases without crashing.