Labwrights · hands-on labs
Each package gives you a small, working app and has you build one production system into it, step by step, on live Azure: the parts demos skip included. Text and code, no video. Every command is run on live Azure before it ships.
Packages
11 labs · about 22–32 h · Azure ≈ $4–14
Early-access price. It goes to $149 at full release.
Build a production RAG system into a real app: ingestion with OCR, hybrid search, cited streamed answers, an evaluation gate in CI, tracing and cost per answer, and layered injection defenses.
Azure OpenAI · Document Intelligence · AI Search · Application Insights
More packages are in progress.
How every package works
Every command is run on live Azure before release, and every expected output in the labs is a real capture.
You build one system into a working app, the way a team would, instead of collecting disconnected snippets.
No video, by design: searchable, copy-pasteable, works offline, and every command is exact.
You run the labs in your own subscription. Each lab states its estimated cost and ends with a teardown back to $0/day.
Each package is a one-time purchase with 12 months of updates, and permanent access to the edition you bought.
Every package has a free lab, with its starting app free on GitHub. Try it first: all sales are final, because the code is yours the moment you pay.
Free guides
A practical map of retrieval-augmented generation on Azure. Which service does each job, in the order your data flows, and the mistake each stage invites.
Why RAG needs both keyword and vector search, how Azure AI Search merges them with Reciprocal Rank Fusion, and real results showing where each one wins.
Call Azure OpenAI with Microsoft Entra ID instead of an API key. The one role to assign, the Python code, and the errors you'll hit on the way.
After checkout you get an invite to the package's private GitHub repository within minutes. Accept it, and the whole package is yours to clone.
No. Each package stands on its own and starts from its own working app. Where a package expects some background, it says so up front, and it's always a skill, never another purchase.
Python basics, comfort in a terminal, and an Azure subscription with billing enabled. Each package's first lab runs entirely on your machine.
No, by design. Text and code is searchable, works offline, and every command is exact.
No course can promise that, and we don't: no promise of employment, interviews, certification, or income. What you get is the skill, and a working system you built yourself and can explain in detail. See the terms.
Yes. Checkout runs through Polar, the merchant of record, so you get a proper invoice for expenses. For a team purchase, email support@labwrights.io.