Tamara Dinneen
The plan

The programme

A reconstruction-first plan run as two stages: design and demonstrate, then rigorous evaluation. Each item is something to understand, rebuild from scratch, and apply. A representative selection is shown here; the full seventeen-week plan is imported from the workbook.

Phase 1Days 1-30

Foundations and the agent atom

Week 1Information retrieval, the evaluation spine, dense versus lexical

FoundationsIR theory and term weighting

Derive TF-IDF and BM25 by hand and explain why each term exists.

Introduction to Information Retrieval (Manning)Self-test: Why does BM25 have a length-normalisation term, and what breaks without it?
EvalThe evaluation spine

Stand up a repeatable retrieval eval harness on your own data.

RAGAS (reference)Self-test: How will you separate retrieval failure from generation failure?
RAGDense retrieval

Explain how dense retrieval encodes meaning and where it fails.

DPR (Karpukhin 2020)Self-test: Why can two passages with no shared words sit close in embedding space?

Comments

No comments yet.

Comments are reviewed before being published.

Week 4Vector search internals, parsing, the agent atom

AgentsReAct loop, the agent atom

Rebuild the reason-act-observe loop from scratch, no framework.

ReAct (Yao 2022)Self-test: What are the failure modes of a naive ReAct loop?

Comments

No comments yet.

Comments are reviewed before being published.
Phase 3Days 61-90 and the rigorous-evaluation stage

The FinanceBench capstone

Week 9Capstone spec and the dismal baseline

CapstoneReproduce the baseline

Show why basic RAG fails on filings, with honest numbers.

FinanceBench (Islam 2023)Self-test: Where exactly does basic RAG break on a 10-K: tables, footnotes, or numbers?

Comments

No comments yet.

Comments are reviewed before being published.