12:24
What Is a Harness? (And Why Should You Care?)
The word everyone in AI throws around and nobody defines. One metaphor and a live build of a real agent, layer by layer, so you can see exactly what each one does.
Watch on YouTubeVideos
The Engineering That Survives the AI Era
The same arguments from the newsletter, worked through out loud: what a harness actually is, what a "job description" for an agent looks like, and the ten skills that don't get automated away.
12:24
12:25
Why Every Developer Feels Like a Fraud (Especially Now)
Impostor syndrome isn't a skill problem, it's a scoring problem: you keep every piece of criticism and give away every win. AI didn't cause it. It just made it louder.
Watch on YouTube
13:19
Most Developers Learn These 10 Skills Too Late
25 years building software, and training developers from day one to senior, distilled into the 10 skills AI can't replace: the ones that decide who thrives as the tools get smarter.
Watch on YouTube
14:15
Stop Resetting Your Claude Code Discount
Claude Code gives you an automatic discount on every session, up to 90% off, and most people switch it off without noticing. The six habits that reset it, the ones that keep it on, and the two screens that show you whether any of it is actually working.
Watch on YouTubeCompanion Series: What Actually Makes an AI Agent Work
Six short breakdowns, one per layer of the harness explained in the video above — the agent definition, the skill, MCP, the context window, governance, and observability.
Part 1 of 6
Your AI agent needs a job description
Part 2 of 6
How to give an AI agent a skill
Part 3 of 6
Why AI agents need permissioned tools (MCP)
Part 4 of 6
Your AI's desk is tiny. That's the context window.
Part 5 of 6
How governance stops an AI from breaking prod
Part 6 of 6
When your AI breaks, follow the trail