Mastery: connect the pieces

1. Idea — Structured output constrains responses to a machine-readable contract such as JSON Schema. It fixes shape; it does not guarantee true or authorized values.…
2. Mechanism — Provide schema/grammar, decode under constraints or validate-and-retry, then run business rules on the parsed object.…
3. Controls — schema strictness, required fields, enums, retries, validators, additionalProperties
4. Tradeoff — Strict schemas simplify downstream code but can make partial answers harder. Large nested schemas consume tokens and reduce model reliability. Retries can repai…
5. Failures — Parse≠truth; Retry double charge
6. Metrics — parse rate, schema-valid rate, business-rule pass, retry count, p95 latency
7. Ship rule — Require integer cents + ISO dates + line-sum check; report parse and schema-valid separately on 1,000 docs.

Neighboring layers (retrieval, serving, policy, human review) still own what structured outputs cannot on the invoice extractor API. Do not ask this chapter’s dial to replace permissions or source truth.

Mastery is transfer: take structured outputs into a second scenario that is not the invoice extractor API and rebuild the checklist without copying sentences. If you can only recite this chapter’s examples for structured outputs, you have memorized a story, not a model.

Also pin one numeric memory from this structured outputs chapter: if 970 of 1,000 outputs parse and 930 pass the schema, parse rate = 97% but end-to-end schema-valid rate = 93%; report both That number is not decoration; it is a template for how claims about structured outputs on the invoice extractor API should look in design docs. Scoped specifically to structured outputs / invoice extractor API / mastery-connect.

People confuse structured outputs with neighboring buzzwords when debugging the invoice extractor API. Before changing prompts, ask whether the broken stage was evidence gathering, the structured outputs judgment itself, validation, or the product action. Fixing the wrong stage creates folklore (“we tried structured outputs and it failed”) that blocks the next team on the invoice extractor API. Scoped specifically to structured outputs / invoice extractor API / mastery-connect.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to structured outputs rather than generic AI advice.

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to structured outputs rather than generic AI advice.