Lesson 28 — Evaluating an AI system: what evidence would convince you?
Unit IV · Grounding

L28_eval.py                                  student     Runs an evaluation set against L26_rag.py; per-item results, totals, and what the set does not cover.
L28_eval_set.txt                             student     Ten-item evaluation set: question, expected document, answer fragment, prediction.
L28_writeup_template.txt                     student     Template for reporting a result with its limitations.

Python 3.11 or newer. Standard library only. Run each program from the folder the lesson tells you to put it in:
    python <file>.py        (Windows)
    python3 <file>.py       (macOS and Linux)
