The leader track 🤝 · for C-level, managers & curious minds · 6 x 45 min · no code, ever
Thinking mode: what RAG actually is, when it beats fine-tuning, what it costs, how to judge whether a RAG system is trustworthy, and how to govern it - each session ends with questions to ask your data team.
What RAG is, and why it beats a bigger prompt
Retrieval in plain English, RAG vs fine-tuning vs long-context, and the one question that tells you when RAG pays off.
🧩 Leader 2 · easyAnatomy of a RAG system
The nine moving parts you fund - ingest, chunk, embed, store, retrieve, rerank, generate, cite, evaluate - each as the question it lets you ask.
💰 Leader 3 · mediumCost vs quality: the real tradeoffs
Where money goes, where quality is won, build vs buy, and the levers that move accuracy without moving the bill much.
📊 Leader 4 · mediumHow to judge a RAG system
Groundedness, citations, hallucination, retrieval quality - the RAG Triad scorecard you demand before you trust an answer.
🛡️ Leader 5 · decidingRisk & governance
PII in embeddings, who-can-retrieve-what, stale answers, vendor lock-in, and refusal as a control you can insist on.
🗺️ Leader 6 · decidingFrom POC to production
The roadmap, the team, RAG vs agents, and where retrieval is heading in 2026 - contextual retrieval and agentic RAG.
The builder track 🛠️ · for practitioners · 10 x 45 min · Python + a browser playground
One growing artifact: Recall, a retrieval assistant. Every session upgrades the same system - and every idea is felt in the in-browser playground first, so the vector database never gets to be magic.
Embeddings 101
What a vector is, why cosine similarity ranks meaning, and why questions rarely share words with their answers. Live playground.
✂️ Builder 2 · easyChunking strategies
Fixed, recursive, semantic, sentence-window, parent-document - size and overlap, and why a bad chunk sinks good retrieval.
🗄️ Builder 3 · mediumVector databases
Chroma end to end - client, collection, add, query - then the pgvector and FAISS deltas, and HNSW vs IVF vs flat.
🔎 Builder 4 · mediumRetrieval basics
top-k similarity search, the retriever interface, and how to read a ranked result set with a critical eye.
🏷️ Builder 5 · hands-onMetadata + hybrid retrieval
where-filters, temporal queries over dated incidents, and dense + sparse/BM25 hybrid with the alpha lever.
🎚️ Builder 6 · hands-onReranking
Bi-encoder vs cross-encoder, retrieve-wide-then-rerank-narrow, MMR diversity, and query expansion / HyDE.
📎 Builder 7 · hands-onGrounding & citations
Answer only from context, cite the source, and the refuse-when-unknown guardrail that kills the confident wrong answer.
🔗 Builder 8 · hardestThe full pipeline
Wire retrieve → augment → generate with the Claude API, and stream one cited, grounded answer end to end.
🧪 Builder 9 · hardestRAG evaluation
A golden set, faithfulness, answer relevancy, context precision and recall, hit-rate and MRR, and the LLM-as-judge.
🚀 Builder 10 · hardestProduction RAG
Re-indexing and freshness, caching, the latency budget, monitoring, and cost - then the handoff to LangChain.
The running project: three escalating corpora 📚
The builder track grows one assistant, Recall, over the same three document sets - each harder to retrieve well than the last.
An MD's chief-of-staff notes
Emails, board notes, travel prefs. Pure semantic search: "what did I commit to in the Q2 board call?" Sessions b1-b4.
Dated Jira incident tickets
Each ticket has a date and a severity. Now retrieval needs metadata and time: "what SEV1s happened in March?" Sessions b5-b6.
A help-center for a support bot
Policy articles a customer bot answers from - grounded, cited, and willing to say "I don't know". Sessions b7-b10.
Choose your path 🗺️
Two doors, one course. Leaders never see code; builders never sit through theory they have not first felt in the playground.
The knowledge map 🧠
Both tracks at a glance - hover a session to spotlight its concepts, click any node to jump in.