Flashcards

A repeatable, structured query that uses metadata columns to answer questions traditional chat AI cannot — like "how many high-risk contracts did we sign last quarter?"

A two-step query that first defines the universe via metadata (e.g. "high-risk contracts"), then analyzes within it (e.g. "how many include indemnification?").

The reason to lock metadata in via extraction. AI re-classification varies per call; stamped metadata gives one stable, governed, auditable answer.

The failure mode where dates buried inside document text are formatted inconsistently. Extraction normalizes them into a real date column so filters become exact.

A query against a metadata column that returns the complete, exact set — not a search-ranked best guess. The property that makes the system usable for compliance.

AI that knows the shape of the library before reading any document — counts, classifications, dates, risks — because metadata was extracted once and now lives in columns.

An AI skill that reads each document as it lands in the library and writes structured fields (risk, type, date, category) onto it. Runs once; the values persist.

The canonical hard question — "find all contracts missing a termination clause." Unanswerable by search (no phrase exists to find absence) and reliably answerable only by metadata.

The reason to extract metadata up front rather than re-read documents per query. Hundreds of files times every prompt equals an unsustainable token bill — and slow answers.

The failure mode where AI relies on text search to answer library questions. Works for "find documents about X" but breaks on absence, counts, and derived-attribute queries.

Retrieval-augmented generation that pulls similar chunks for each question. Strong for conceptual lookup; weak for counts, dates, negation, and filtered aggregates.

Ordinary SharePoint columns populated by an AI extraction skill. They look like any column but their values come from a governed prompt run against the document text.