Latest episode
How to Talk AI Agents to Find Sneaky Production Bugs | S2E9
A two-week unreproducible mobile bug, 30 hours of agents, and the rules Ran uses so “done” means proof — not vibes.
Old School / New Tech
Software Factories - Lights Out or Lights On? | S2E8
Lights-out AI software factories produce slop; Ran’s lights-on loop keeps humans at plan and PR — and refuses to automate that gate.
Old School / New Tech
Company-Scale Agentic AI (method + free book) | S2E7
Company AI fails less from dumb models than from blind ones — and how to build the observe → understand → build → run → compound loop.
Old School / New Tech
How I Work: My Solo Dev Setup, Time Management, and Running Companies | S2E6
Remote “local” setup, coding harnesses, automation buckets, and why most of his job is classifying work — not typing it.
Old School / New Tech
I built an Open-Source Secrets Tool (Live Session) | S2E5
Live build of a Git-native tool that encrypts .env values in the repo and restores plaintext locally — from empty repo to production-level tool
Old School / New Tech
AI Adoption is not something you buy | S2E4
Why corporate AI fails at the people layer — pick one tool, fit it to how you already work, measure outcomes not tokens, and stop chasing every new model.
Old School / New Tech
Meet the CLI – the Cockroach of Interfaces | S2E3
Why the Terminal Never Dies: CLI Power, AI Agents, and Practical Guardrails
Old School / New Tech
The New Org Chart: Embracing a System-Driven Model | S2E2
How the industry shift from traditional org charts to a system-driven, AI-assisted “pod” model where early-stage companies focus on just builders and sellers, deferring classic middle management until roughly 20–30 people.
Old School / New Tech
AI and the Open Source Frontier (Live and Unedited) | S2E1
Old School New Tech Returns: Live Format, MUXI Agent Server, and Open Source Licensing Debate