Extract Llm Structured

Agent calls /v1/extract to pull product name, price, and SKU but passes a vague prompt with no schema, getting back free-form text it must re-parse.

Provide an explicit JSON Schema (fields, types, required) so /v1/extract returns validated structured output keyed to the schema. The schema is the contract; the prompt clarifies intent. Validate the result against the schema before use.

The schema asks for 'founded_year' but the prompt says 'extract the company's age in years', producing inconsistent outputs.

Keep prompt and schema aligned: the prompt should describe how to populate the exact schema fields, not a different derived value. Ambiguity between prompt and schema yields unreliable extraction; reconcile them to one contract.

A required schema field has no corresponding value on the page. The model fills it with a plausible-but-invented value.

Prefer null/empty for fields absent from the source over fabricated values; validate against the schema and flag low-confidence or unsupported fields for review. A confidently wrong value is worse than an explicit gap.