NOTES
Notes from the studio.
What we learn building software and AI that companies run every day: decisions, mistakes and the method behind them.
- 01The gap AI leaves: why a prototype is not a productAI builds a prototype in hours. Surviving real users, fitting your systems and growing with the company is another job. Here is what it takes.Read
- 02How we built the Open Data AgentA Claude agent that queries public data in real time without the server paying for a single token. The architecture, nine tools and the trade-offs.Read
- 03A method from NASA for building with AIWhen AI writes the code, the expensive mistakes move to design. What we inherited from NASA systems engineering, and where the human stays in the loop.Read
- 04Keeping the cost of AI under controlTokens, caching, model routing and budgets, explained for decision makers. Mechanisms documented by the providers, with no invented prices.Read
- 05Teaching AI for real projectsWhy every guide ends in a project, how the paths are organized by role, what workshops are for, and how to choose where to start.Read