MESA LEARN / A CONNECTED COURSE
Understand memory.
Build with evidence.
From your first question about AI memory to a search system you can run and inspect. One course, concrete examples, no assumed background.
14 lessons · read in order or explore by question
Learn one idea.
Then make it work.
- 01 / Follow the example
The fictional Atlas archive connects the lessons. Track the same source as it becomes a record, a search hit and evidence.
- 02 / Check your reasoning
Calculate the worked examples, then try each question before opening its explanation.
- 03 / Build and verify
Finish with a Python/SQLite lab. Keep the source IDs, inspect failures and measure what actually changed.
THE COURSE LIBRARY
Start at zero.
Or follow your question.
Start from zero
Context, RAG and source-linked records
- 01
AI memory: what survives after a conversation?
Distinguish model weights, the current context and persistent records. Design a memory write before choosing a database.
- 02
RAG and memory: build the request step by step
Trace a source from retrieval into an answer. Learn why RAG and memory overlap, how context budgets work, and where grounding can fail.
- 03
From documents to claims: preserve what extraction loses
Represent exact text, entities and assertions without confusing an extracted claim with verified truth. Work through a source-linked record.
Learn to retrieve
Represent, rank, fuse and follow relations
- 04
Embeddings and semantic search, with numbers
Calculate similarity, distinguish dense and sparse representations, and understand why nearest neighbors are neither facts nor access decisions.
- 05
BM25: why a rare word can beat repeated words
Work through term frequency, rarity and length normalization. Tune tokenization and field weights before chasing a larger model.
- 06
Hybrid retrieval: candidates, fusion and reranking
Design a search pipeline where lexical and semantic lanes contribute different evidence. Diagnose whether recall, fusion or reranking is failing.
- 07
Reciprocal Rank Fusion: calculate and inspect every vote
Fuse two ranked lists by hand, handle duplicates and ties, and understand why an RRF score is not confidence.
- 08
Knowledge graphs: follow relations without inventing proof
Build a source-linked graph, trace a two-hop question, and distinguish graph traversal from GraphRAG summaries and valid inference.
Build trustworthy systems
Evidence, permissions, durability and change
- 09
Evidence and provenance: what a citation actually proves
Build a verifiable citation with source revision and exact span. Distinguish integrity, provenance, claim support and source truth.
- 10
Shared memory: who may retrieve what?
Trace identity, roles and dataset scope through retrieval, caches and graph paths. Test isolation before measuring relevance.
- 11
Canonical storage and projections: survive a partial write
Trace one mutation through SQL, vector and graph stores. Understand durable admission, retries, idempotency and projection rebuilds.
- 12
Changing facts: validity, contradiction and forgetting
Distinguish when a statement applies from when it was recorded. Handle corrections and conflicts without equating age with invalidity.
Measure and build
Judge retrieval and run your first lab
- 13
Evaluate retrieval: recall, MRR, nDCG and latency
Calculate ranking metrics on a judged list, separate quality from speed, and design an experiment that does not grade its own training examples.
- 14
Build a small search lab, without an LLM
Run a complete Python/SQLite example, predict its results and add a judged regression case. Connect the course concepts to an inspectable program.
No lesson matches. Try fewer words, a different term, or clear the stage filter.
