Josh came in with one goal: resist showing us the 3D demo he spent two weeks building. He succeeded. Barely.

Instead we talked about the actual interesting stuff — why he's building systems for AI agents instead of humans, how a mech arena became his favorite benchmarking tool, and what happens when you let Claude playtest your game engine for you.

Also: two Blackwell GPUs, a Glicko rating system, and the most cursed MMORPG premise we've ever heard.

• 00:00 Intro — Mike's late, just Joe and Josh
• 01:04 Six weeks later: redefining success
• 02:34 Enter Matt, the PM partner
• 04:35 Federated agents and the mech arena
• 07:44 BattleBots but autonomous
• 09:20 Why he killed the 3D demo
• 17:32 Mike finally shows up
• 20:58 How the arena actually works
• 24:55 Josh's model stack and hardware ceiling
• 35:48 Monday idea, Friday artifact
• 38:23 BYO LLM: prompt it, throw it in, watch it lose
• 43:15 Tournaments, ratings, Steam for agents
• 51:28 Token fight economics
• 54:16 Three-day POC rule and wrapping up

Mike shares his recent deep dive into AI tools like Claude, exploring how he's integrating them into work processes, building AI-driven workflows, and lessons learned along the way. The conversation covers practical strategies for leveraging LLMs, managing code projects, and enhancing communication and project management with AI.

• 00:00 Introduction and Personal Updates
• 03:17 The Impact of AI on Work Habits
• 06:11 Learning and Teaching AI Tools
• 09:21 Building an AI Guild at Work
• 12:10 Problem Solving with AI
• 18:17 Creating a Google Form with AI
• 24:08 Iterating and Improving Processes with AI
• 28:20 Planning and Context Management in AI Usage
• 30:45 Navigating AI Tools for Project Management
• 32:00 Creating Effective Project Roadmaps
• 34:53 Leveraging AI for Code Analysis
• 38:43 Integrating AI with Data Sources
• 41:43 Focusing AI's Attention on Relevant Information
• 44:46 Optimizing AI for GitHub and Snowflake Access
• 48:57 The Role of AI in PR Management
• 53:39 Trusting AI: The Need for Human Oversight

Mike recently got access to Claude Code at work — and as a non-engineer, he's been using it in ways nobody expected. In this episode, Mike and Joe break down what happens when a PM starts interrogating the codebase, from learning how systems actually work to catching years of organizational mythology that turned out to be wrong. They explore practical use cases for non-technical folks — market research, data access, UI mockups — and get into the weeds on Mermaid diagrams, hallucination strategies, and sub-agents. They also both happen to be starting AI Guilds at their respective companies, and have a lot to say about why bottom-up beats top-down when it comes to AI adoption.

00:00 Intro & The Flowchart Problem01:29 Mike Gets Claude Code Access06:45 Use Cases for Non-Engineers09:30 Market Research & Data Science with AI Agents11:25 Read-Only Database Access: What's Safe?13:00 Two Challenges: Threading & Hallucination15:25 How to Pressure-Test AI Answers17:45 Mermaid Diagrams Explained21:44 Mermaid in Notion23:49 Building an AI Guild at Work28:46 Sub-Agents & Avoiding Hallucination30:23 Wrap Up & What's Next