Learn prompt engineering. The production version, not the LinkedIn one.
Moonlabs is the operator-led AI Academy in Derby. We run three live companies — Homemove, home.co.uk and homedata.co.uk — and we teach twelve students per cohort to ship a real AI product, sell it to a real customer, and raise on it. Three pillars: Coding, Commercials, Investment. Twelve weeks. £6,000.
Moonlabs is what we are. Two operators — James Freestone and Louis O’Connell-Bristow — who run Homemove, home.co.uk and homedata.co.uk, have raised £5m+ for their own companies, and have been AI-native in the editor since the week ChatGPT shipped. Every customer surface and internal tool at all three is prompt-engineered.
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. Almost every ‘learn prompt engineering’ resource on the internet stops at the wrong place. A prompt that works on a screenshot is not a prompt that works in production. The hard parts — evals that catch regression, structure that survives a model swap, retries that do not loop, schema validation that does not silently corrupt downstream data, prompt-injection defence, observability, cost discipline — are everything the LinkedIn screenshots never show. Those are the bulk of the course.
Coding · production prompt engineering
Structured outputs, JSON-schema, tool calls, eval suites from week one, retry strategies that do not loop, prompt-injection defence, model portability, observability. A deployed prompt-engineered product by week twelve — using the patterns we use to run three live companies.
Commercials · selling prompt engineering as an offer
Prompt engineering is the rare AI skill an SMB will write a cheque for next week. Pricing a prompt-engineering retainer, the discovery call, a one-page pilot agreement, the first paying customer. A paid pilot by week six — with prompts you wrote running over their data.
Investment · raising on a prompt-engineered product
Cap table, ten-slide deck, financial model, term sheets. Investors fund products, not prompts — so we wrap your prompt work inside a real customer story with a real wedge. We make warm introductions to UK angels who actually write cheques. A live investor pipeline by demo day.
Common questions.
I have read every prompt engineering guide on the internet. Will this still help?
Probably yes. The internet guides almost all stop before evals, retries, schema discipline, prompt-injection defence and model portability — the things that distinguish a screenshot from a system. Those are the bulk of the course.
Do you teach Anthropic-style prompts, OpenAI-style, or both?
Both. The course is provider-agnostic — Claude, OpenAI, open-weight models all appear. The patterns are about the underlying systems thinking, not the brand on the API.
Will I learn agents and RAG alongside?
Yes — both are central to the broader curriculum. The agents course and RAG course pages are sister framings of the same twelve weeks.
Is this aimed at engineers or non-engineers?
Both, by design. The on-ramp with current tooling is short enough that non-engineers can ship production prompt-engineered systems inside twelve weeks. Engineers reach a higher ceiling in the same time. The course meets you where you are.
Will the course go out of date?
The tooling will. The disciplines — evals, structure, observability, portability — will not. We refresh the tooling each cohort.
More Academy entry points.
The Academy is one course with many doors. Each of these pages is a different entry point into the same twelve weeks.
Build it. Sell it. Raise on it. In twelve weeks.
Tell us what product you would prompt-engineer and who would pay for it. James and Louis read every application personally and reply inside the week.
© 2026 Moonlabs Incubator. All rights reserved.