The OpenAI API. Past hello-world, into production.

Moonlabs is what we are. Two operators — James Freestone and Louis O’Connell-Bristow — who run Homemove, home.co.uk and homedata.co.uk. The OpenAI API is a production dependency at all three businesses; the patterns on this page are the ones we use to keep the bill, the latency and the regressions inside the lines we promised our users.

The Academy is what we do. A twelve-week, in-person, twelve-student cohort in Derby. You build a real AI product. You sign a paid pilot on it. You write a deck and a financial model. You leave with a deployed system, a paying customer reference and a live investor pipeline. Coding, Commercials, Investment — the three pillars taught in equal weight every week.

Why this page exists. Most engineers’ first encounter with the OpenAI API is ‘curl a chat completion, parse the JSON, done’. That gets you to hello-world. Production OpenAI is a different discipline: the Responses API and its stateful conversation model, function-calling that retries without looping, JSON-schema validation, the Agents SDK when it earns its place, streaming the front end can consume, observability that explains what the model decided. You leave the Academy with an integration in production for paying users, gated behind evals you wrote yourself, and the muscle memory to handle a model release without breaking last week’s ship — or as the founder of a GPT-shaped product.