Nothing is edited out
The dead ends and the corrections stay in. That is where the useful judgment lives, and it is the part every polished demo removes.
Real applications, built on camera, with AI as an active partner.
Most AI demos are five minutes long and skip the part where it goes wrong. AI in the Lab does the opposite. Each series takes on something substantive, a complex application build, an agent workflow, a real tool, and shows the whole orchestration end to end, including the parts that stall.
All code and reference documents are shared in public repos, so you can clone what gets built rather than take my word for it.
Episode 1
90 minutes ยท Watch on YouTube
Series 1 is an automated crypto trading app, built with AI as an active partner from the first conversation, across several planned episodes.
Episode 1 covers the concept conversation, the high-level plan, and Phase 1 of the build. It walks the concept through to a defensible plan, then the plan through to a runnable artifact: a working UI with a real-time TradingView-style chart that you can clone from the repo.
Disclaimer: Educational only. Not investment advice.
The dead ends and the corrections stay in. That is where the useful judgment lives, and it is the part every polished demo removes.
Code and reference documents go into public repos. If something works on camera, you can run it yourself.
The same methods I use in client work and in my own practice, applied to a real application rather than a toy example.
Founder of AdviceForge and former CEO. I have spent the past several years informally advising fellow founder-CEOs in the Abundance360 community on their AI adoption work. AI in the Lab is me doing the building in the open, so you can judge the work rather than the claims.
I write at adviceforge.com about why team AI capability is the actual constraint on AI ROI. More about me.
See how I work with small-to-mid-market companies as a fractional Chief AI Officer, or book a call.