Build the first working RAG quality audit report

Build only what the claim requires: audit records hit/miss per question with docs_version and fails release under threshold. Prefer boring, deterministic code over frameworks you cannot yet explain. Run the path twice; identical output on this fixture is a feature, not a lack of creativity.

gold=[('When open?','hours'),('Wifi?','wifi')]
candidate=[('When open?','hours'),('Wifi?','parking')]
hits=sum(g==c for g,c in zip(gold,candidate))
print({'citation_hits':hits,'n':len(gold),'docs_version':'faq-2026-07-18'})

Expected evidence: citation_hits 1 / n 2. Read each printed intermediate as part of the argument that the path works—not as decoration.

Narrate the journey from raw input to result for a single example from gold set with expected evidence IDs + candidate run output. If you cannot name an intermediate, the implementation is still too opaque for this lab. Only after this path is solid should you generalize data sources or UI.

While implementing the RAG quality audit report, print or log at least three intermediates that map to the claim (audit records hit/miss per question with docs_version and fails release under threshold). Good intermediates are values a teammate could recompute with a calculator or diff. Bad intermediates are framework traces you cannot explain.

Re-run with gold set with expected evidence IDs + candidate run output twice. If the second run differs, either the path is nondeterministic (document the seed) or you have hidden global state—both are lab bugs until named.

Stop adding features once the path supports turn golden questions, expected evidence IDs, and citation checks into a release artifact. Extra UI, extra tools, or extra models belong in later chapters. The mastery bar for this page is simply: a deterministic end-to-end path with intermediates.

At the implementation stage for rag-quality-audit, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about gold set with expected evidence IDs + candidate run output that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: previous docs_version audit score.

For this page specifically, success looks like a deterministic path with printed intermediates while still centering the user decision to turn golden questions, expected evidence IDs, and citation checks into a release artifact. If you cannot point to a file, command, or assertion that proves that for the RAG quality audit report, stay on this page instead of advancing.

Glossary: faithfulness · Glossary: recall@k · Cheatsheet: RAG quality · How-to: evaluate RAG quality

Previous · Next