AI EngineerGuide

Turn a classifier's structured-output schema into decision questions

Paste the structured-output schema, tool definition or bare JSON Schema your classifier uses. Each field becomes a decision question or is marked keep in LLM, and you get the request in the format you pick.

Runs in your browser. Nothing you paste is uploaded.

Converted request
Paste a request body, a structured-output schema, or a tool definition. Remove secrets first. Nothing leaves your browser.
curl
How the answers come back
QuestionOpenAIGeminiJev / Clef
Yes/no{type: "predicate", name, probability}{type: "noul", noul (0.01–0.99), confidence}{type: "noul", noul}
Pick one{type: "choice", name, choice, probabilities: [{value, probability}], confidence}{type: "choice", choice, probabilities: {option: p}, confidence}{type: "choice", choice, confidence, probabilities: {…}}
Ordered rubric{type: "score", name, score, probabilities: [{value, label, probability}], confidence}{type: "score", score, legend: {"0": …}, probabilities: {"0": p}, confidence}{type: "score", score, confidence, legend, probabilities}
Refusal{type: "refusal", name} (name is null for an unnamed question)not documentednot documented
Containerarray, in question ordermap keyed by question idmap keyed by question name (Clef wraps the response in result: unconfirmed)

17 warning types. Most link to the provider's docs; format facts come from the sources listed on each format pair page (last checked 2026-11-19).

How to use it

  1. Paste your schema. An OpenAI response_format or text.format, an Anthropic tool input_schema, a function tool’s parameters and a bare JSON Schema all work.
  2. Check the mapping table. Tick Ordered? for an enum whose values have an order (low, medium, high) to ask a score question instead of a choice.
  3. Rewrite any placeholder question, then copy the request for the API you picked.

How the mapping works

Each leaf of the schema is mapped the same way every time:

Schema fieldBecomes
string with an enum of 2 or more valuesPick one (or score, when you tick Ordered?)
booleanYes/no
integer with minimum/maximum within 10 levels, or an integer enumScore, one level per value
array of enum valuesOne yes/no per value
number named like confidence, probability or certaintyDropped: the API returns it
Anything elseKeep in an LLM step

Question keys are the field path joined with _, then sanitized for the target API. Questions without a description get a placeholder you should rewrite. The input is set to <paste the text you classify>.

Convert a request between formats instead.

FAQ

Which classifier fields can a decision API answer?

Enums (pick one), booleans (yes/no), small integer ranges or integer enums (score), and arrays of enum values (one yes/no per value). Objects with properties are walked, so their enum, boolean and integer fields become questions too. Free text, other numbers and objects without properties need a generative step.

What happens to my `confidence` field?

A number field named like confidence, probability or certainty is dropped (an integer or enum one still becomes a question). Decision APIs return probabilities and confidence for every answer, so you don’t ask for them.

What about nullable enums?

For a pick-one question, the converter adds an other option (unless the enum already has one). A field you mark Ordered? becomes a score with no other level. OpenAI recommends a fallback option such as "other" when your categories don’t cover every possible input.