LlamaIndex. Retrieval pipelines that ship.
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. homedata.co.uk is the property-data layer underneath both consumer products — ingestion, parsing, indexing and retrieval at scale is the day job. The patterns on this page are the ones we use ourselves.
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. LlamaIndex sits in a different slot from LangChain — where LangGraph is the agent-orchestration layer, LlamaIndex is the retrieval-pipeline-as-product framework. Ingestion connectors, parsers, indexers, query engines, routers, evaluation harnesses. Production teams that take retrieval seriously end up running some version of this stack, framework or hand-rolled. You leave the Academy fluent in retrieval engineering — or as the founder of a vertical-search product whose moat is the corpus you wrangled into shape.
Coding · LlamaIndex at production fluency
Document ingestion at scale, chunking strategies, hybrid lexical + vector retrieval, reranking, query routing across indices, citation-aware synthesis, LlamaIndex Agents where they earn their place. Retrieval-level evals from week one because most teams eval the generation and ship a broken retriever. A deployed retrieval system by week twelve.
Commercials · vertical-search as a productised offer
Every SMB with a knowledge base, a policy library or a customer-support archive is one good retrieval system away from a transformative product. Pricing a vertical-search retainer, the discovery call, a one-page pilot agreement, the first paying customer. A paid pilot by week six — for many graduates, sold back into a sector they already know.
Investment · raising on retrieval-AI
Glean ($4.6bn, enterprise search), Vectara, Pinecone ($750m+), Weaviate, Chroma raising on the embedded-vector thesis, Hebbia ($130m on document retrieval), Sourcegraph, You.com, Perplexity ($14bn) — retrieval-AI is one of the largest funded categories of the cycle. Cap table, ten-slide deck, financial model. A live investor pipeline by demo day.
Common questions.
Is LlamaIndex right for every retrieval system?
No — simple one-document retrieval often does not need a framework, and serious teams sometimes outgrow LlamaIndex and hand-roll. We teach the judgement on when it earns its place. The RAG curriculum is the wider framing.
How does LlamaIndex compare to LangChain?
Different jobs. LangChain (and LangGraph) is the agent-orchestration layer; LlamaIndex is the retrieval-pipeline layer. Many production teams run both, with LlamaIndex feeding retrieval into a LangGraph agent. We teach both. LangChain page; LangGraph page.
Will I learn agents built on top of LlamaIndex?
Yes — LlamaIndex Agents are first-class in the framework now, and we teach them where they earn their place against provider-native or framework-agnostic alternatives.
Do I need to know Python or TypeScript?
Either is fine — LlamaIndex has first-class support for both. Your project shapes the choice.
What if LlamaIndex changes significantly during the cohort?
It will — this space moves fast. The course is built around the durable retrieval-engineering patterns (chunking, embedding, reranking, evals) which transfer cleanly between frameworks. Tooling is refreshed 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 corpus you would retrieve over and who would pay for it. James and Louis read every application personally and reply inside the week.
© 2026 Moonlabs Incubator. All rights reserved.