Structured Output

Parent: Agentic.

Structured Output forces models into JSON/schema-shaped answers so downstream systems can execute without brittle parsing. Under Agentic it is the contract layer between LLMs and tools/workflows. It is not Guardrails (safety policy) though both may reject bad outputs.

Technically compare constrained decoding, validators, repair loops, and schema DX. Failure modes: “JSON mode” that still drifts fields, silent coercion, and schemas so loose they accept garbage.

Members: Instructor, Outlines, Guidance, LMQL. Prefer constrained decoding when validity is non-negotiable; prefer validator+retry when models are strong but occasional repairs are cheap.

Feature maps such as Verify business effect, not API 200 mark why this cell exists: typed payloads into execute gates. Pair with Evaluations so schema adherence is measured, not assumed.

Inline members for audit: Instructor Outlines Guidance LMQL. Features: Verify business effect, not API 200 Finance & Accounting Insurance. Related terms referenced: Frameworks, Guardrails, Evaluations.

For this research catalog the acceptance test is boring and strict: after wiring the pack, can a second person replay the same scenario and get the same measurable outcome? If not, the page is still a brochure. Document the scenario, the expected number, and the log line that proves it. That habit is what separates a deepened taxonomy cell from a landscape screenshot.

Also record what you refused: tools not connected, corpora not ingested, metrics not collected. Refusals keep the cell honest when marketing pages claim universality. A taxonomy essay that only lists winners teaches less than one that names the skip conditions next to the install path.

Keep the essay technical enough that an engineer can argue install order — and short enough that a reader finishes it before opening the right-rail member list. Prefer primary docs and repo evidence over landscape blurbs when the right-rail packs disagree.

Operational discipline for this cell: name the install artifact, the health check, and the rollback. Prefer one golden path documented against a member pack in the right rail over five half-wired demos. When packs disagree, believe the primary repository README and a failing test you can re-run — not the landscape one-liner. Measure latency, cost, and error rate on a frozen scenario before declaring the subcategory “covered.” If you cannot point at a log line that proves the scenario, the essay is unfinished even when the word count clears the audit floor.

Cross-link greedily but honestly: every taxonomy wikilink should change a reader’s next click, and every pack slug should resolve to a real pack. Do not invent members to decorate the prose. Prefer fewer true links over many decorative ones. Keep Monday-shaped typing out of the runtime story; observation and ledger remain senior to any agent UI that retypes reality.