Full workshop
How to Build With AI Without Losing Control
A practical workshop on solving real problems with AI, avoiding lock-in, and giving agents goals they can verify.
A 5-minute workshop on using AI to ship real software without getting stuck in tools, vague prompts, or one-agent-at-a-time work.
Start from a daily problem
AI coding is useful when it starts with something you already hit: a messy workflow, a repeating chore, a rule a spreadsheet cannot hold. The first move is not “learn to code.” It is “name the problem.”
Roommate bills
Splitting rent and utilities equally is the wrong model when people are in and out. Presence-aware rules are a better fit — and a small enough problem that building a tool for it is now worth it.
Curiosity beats assumed limits
People who have not been trained on what software “cannot do” often try stranger things. That curiosity is an advantage if you keep checking the result.
Do not get locked in
A hosted demo is fast. Production is where the trap shows up: one vendor, one model, one place your files live. Prefer tools you can leave.
Give the agent a goal you can verify
Tiny step-by-step instructions age badly. A specific target plus an observable test lets the agent keep working without you narrating every file.
Let it test what it builds
Browser tools and a clear check close the loop. The agent builds, runs, and only stops for a real blocker.
Run parallel agents
If the work splits cleanly, try several implementations at once. Pick from evidence, not from the first draft that compiled.
Managing agents is management
Several agents need shared goals, ownership, and a merge path. That is a coordination problem, not a prompt trick.
AI makes you think more
Faster execution packs more decisions into each day. The work does not disappear. The judgment gets denser.
Practice, not a one-off app
The first live URL is the start. Skill comes from repeating small builds, watching them fail, and keeping the ones that hold.