Closed beta for adults · free
Build a RAG system you can trust
Chunking, hybrid search, reranking, citations and evaluation — in the order they build on each other. The diagnostic skips what you already know.
Sound familiar?
What you can do afterwards
The goal covers 77 knowledge nodes from the basics up, roughly 58 hours if you start from zero. The diagnostic removes what you already know.
- DBM25 and keyword search
- DBuild a small search engine
- EStoring and finding vectors efficiently
- EChunking documents
- EHybrid search and RRF
- FReranking with cross-encoders
- FChoosing and fine-tuning embedding models
- ERAG — retrieval-augmented generation
- ECitation and grounding
- FKnowledge graphs and graph RAG
- FLong context versus retrieval
- FEvaluating RAG answers
- EEvaluating retrieval: recall@k, MRR, nDCG
- EIndex updating and versioning
Labs along the way
You write the code in the browser or in a sandbox on the server. Hidden tests decide whether it holds up.
What you get
Diagnosis first
The questions follow the prerequisite chain back from the goal. You skip what you already know.
The shortest path
Only the knowledge you are missing, in the order it builds on itself. The path is recalculated as you learn.
Labs with hidden tests
You write the code. Tests you cannot see decide whether it holds up — not whether it looks right.
Proof of what you can do
Mastery requires several kinds of evidence. The certificate lists them and can be verified.
See where you stand — in ten minutes
No account. You see right away what you already know and where your path would start.
Chunking, retrieval evaluation, citation and grounding — the whole chain from document to answer with traceable sources.