LangChain. When it earns its place.
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. We run both LangGraph and provider-native AI in production across these three companies — the framework-versus-native judgement on this page is the one we make in our own codebases every week.
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. LangChain was the punching bag of AI Twitter for two years and most of the criticism was fair — over-promoted, over-abstracted, an entire generation of agentic systems no-one could reason about. The framework has matured; LangGraph in particular has a real claim on the multi-step orchestration problem. You leave the Academy with the judgement to use it when it earns its place, the muscle memory to swap to provider-native when it does not, and the portfolio piece to back the call.
Coding · LangGraph + provider-native, both fluent
LangGraph for multi-step orchestration with debuggable state machines. Anthropic and OpenAI SDKs directly for single-shot generation and tool-use loops where every millisecond counts. Evals from week one, observability across both stacks, and the muscle memory to swap. A deployed system on whichever stack made sense, by week twelve.
Commercials · orchestration as a productised offer
LangGraph-shaped consulting engagements (audit / port / rebuild) are the new high-ticket retainer at AI-native shops. Pricing the engagement, the discovery call, a one-page pilot agreement, the first paying customer. A paid pilot by week six — for many graduates, sold back into an SMB drowning in v0-era LangChain code that needs cleaning.
Investment · raising on AI orchestration tooling
LangChain itself raised $25m+ at $200m+; Vellum, Voiceflow, Inworld, AutoGen-style frameworks all funded; Mastra raising on the agent-orchestration thesis; Pulumi shipping AI primitives; Reka, Replicate, Modal Labs all on the orchestration-adjacent layer. Cap table, ten-slide deck, financial model. A live investor pipeline by demo day.
Common questions.
Is LangChain dead?
No, but it is no longer the default. LangGraph is genuinely the strongest multi-step orchestration option for many production cases; LangChain core is still useful for specific integrations. The honest version is: it depends on the project, and we will teach you to decide.
Will I learn LangGraph specifically?
Yes. LangGraph is where the framework earns most of its place in production AI in 2026 — state machines, debuggable agent flows, framework-managed memory. We cover it in depth alongside provider-native alternatives.
How does this compare to your other framework pages?
Same Academy, different tool focus. MCP is the protocol layer; agents is the architecture layer; LangChain / LangGraph is the orchestration layer. They overlap but each is a different framing.
Will I learn LlamaIndex too?
Lightly, where it earns its place. LlamaIndex has a strong claim on the retrieval-pipeline-as-product space; we cover it as an alternative in the RAG part of the curriculum.
What if the framework I learn here gets deprecated next year?
It might — this space moves fast. The course is built around the durable patterns (orchestration, state, evals, observability) 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 you would build and we will talk through whether LangChain is the right answer. James and Louis read every application personally and reply inside the week.
© 2026 Moonlabs Incubator. All rights reserved.