> ## Documentation Index > Fetch the complete documentation index at: https://docs.omnia-voice.com/llms.txt > Use this file to discover all available pages before exploring further. # Create a criterion > One binary question about quality. A criterion's verdicts are meaningless until you ALIGN it against your labels — create, then POST /v1/criteria/{id}/align. ## OpenAPI ````yaml /openapi.json post /v1/criteria openapi: 3.1.0 info: title: Omnia Management API description: >- The management API behind the improvement loop: capture and setup, request logs and datasets, grades (labels), judges (criteria), evals and deploy gates, fine-tuning and reinforcement learning, dedicated GPU endpoints, and model aliases and versions. Authenticated with a workspace API key (sk_sovereign_...). The inference API (chat, embeddings, rerank, responses) is OpenAI-compatible and documented separately. Responses are snake_case, list endpoints on the loop products use the {"object": "list", "data": [...]} envelope, and refusals use the same nested error shape the gateway emits: {"error": {"message", "type", "code"}}. Request bodies on the loop products (logs, labels, criteria, evals, datasets, aliases) are snake_case; the training and infrastructure products (fine-tuning, GRPO, environment tools, dedicated, model-version adoption) validate camelCase bodies, and each schema below says which it is. Endpoints that spend money require a key minted by a workspace owner or admin and return 403 otherwise. version: 1.0.0 servers: - url: https://gateway.omnia-voice.com description: Production - url: https://platform.omnia-voice.com/api description: Production (legacy alias — same API, older base URL) security: - bearerAuth: [] paths: /v1/criteria: post: tags: - Criteria summary: Create a criterion description: >- One binary question about quality. A criterion's verdicts are meaningless until you ALIGN it against your labels — create, then POST /v1/criteria/{id}/align. operationId: createCriterion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateCriterion' responses: '201': description: The draft criterion. content: application/json: schema: $ref: '#/components/schemas/Criterion' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' components: schemas: CreateCriterion: type: object required: - name - judge_prompt - judge_model properties: name: type: string maxLength: 80 description: type: - string - 'null' maxLength: 500 judge_prompt: type: string minLength: 10 maxLength: 4000 example: >- FAIL any response that never delivers a final answer — e.g. it consists only of reasoning, stops mid-sentence, or is cut off before answering. judge_model: type: string example: Qwen/Qwen3-235B-A22B-Instruct-2507 unit: type: string enum: - request - trace description: >- Create-only. Trace-unit judges read whole runs and align against whole-run labels. population: type: string description: >- Tag scoping what the judge scores online and which labels it aligns against. population_family: type: string description: >- Auto-detected traffic segment scoping what the judge scores online and which grades it calibrates against — a `segment` value from GET /v1/logs; '' = no segment scope. Composes with population (tag). Criterion: type: object properties: id: type: string name: type: string example: Complete final answer description: type: - string - 'null' judge_prompt: type: string description: >- The binary instruction the judge applies. State precisely what makes a response FAIL. judge_model: type: string status: type: string enum: - draft - retired description: >- Lifecycle only: draft (in use) or retired (excluded from online scoring and pickers; set via PATCH). Alignment QUALITY is never stored here — read tier, tpr, tnr, and aligned_at. A criterion can be fully aligned and still say status=draft; that is by design, not a missing promotion. source: type: string enum: - human - assist_suggested tier: type: string enum: - aligned - weak - misaligned - unmeasured description: >- LEGACY point-estimate badge, kept for continuity. Computed by comparing the raw TPR/TNR to fixed thresholds, so it cannot distinguish 9-of-10 from 90-of-100. Read `trust` instead — that is what every gate uses. trust: type: string enum: - trustworthy - under-measured - borderline - misaligned - unmeasured description: >- What this judge's evidence PROVES, derived from the 95% Wilson interval rather than the point estimate. `trustworthy` = both lower bounds clear the 90% bar. `under-measured` = straddles it, and more grading would settle it (see fail_grades_needed / pass_grades_needed). `borderline` = straddles it with the rate hugging the bar, so more grading will NOT settle it — narrow what the judge asks instead. `misaligned` = an upper bound sits below the bar, i.e. proven wrong rather than merely unproven. `unmeasured` = no interval at all (never calibrated, or one-class grades). Auto-routing and RL rewards require `trustworthy`; dataset curation also accepts `under-measured`. tpr_ci: type: - array - 'null' items: type: number minItems: 2 maxItems: 2 nullable: true description: >- 95% Wilson interval [low, high] for `tpr` — the evidence `trust` was derived from. Null when no human-failed grades exist. A tpr of 1.0 with tpr_ci [0.646, 1.0] means the judge caught every failure it was shown, and was shown seven. tnr_ci: type: - array - 'null' items: type: number minItems: 2 maxItems: 2 nullable: true description: >- 95% Wilson interval [low, high] for `tnr`. Null when no human-passed grades exist. fail_grades_needed: type: - integer - 'null' nullable: true description: >- Additional grades OF FAILING TRACES needed for TPR's lower bound to clear the bar, assuming the judge keeps its observed rate. TPR is measured only on human-failed rows, so grading more passes does not move it. Null when already proven, already below the bar, or too close to it for grading to help. pass_grades_needed: type: - integer - 'null' description: The same for TNR, measured only on human-passed rows. tpr: type: - number - 'null' description: >- P(judge says fail | you said fail) — how often it catches real failures. tnr: type: - number - 'null' description: P(judge says pass | you said pass). kappa: type: - number - 'null' description: >- Cohen's κ — chance-corrected agreement (raw agreement is inflated by class imbalance). alignment_n: type: - integer - 'null' aligned_at: type: - string - 'null' format: date-time created_at: type: string format: date-time unit: type: string enum: - request - trace description: >- What this judge grades: one exchange, or a whole agent run / trace-grouped conversation. Fixed at creation. population: type: string description: >- The tag this criterion judges online AND aligns against ('' = all logged traffic). Changing it voids alignment. population_family: type: string description: >- The auto-detected traffic segment this judge is scoped to ('' = none): a `segment` value from GET /v1/logs. Scopes what it judges online AND which grades it calibrates against, together with population (tag) and unit. Changing it voids calibration. online_enabled: type: boolean description: >- Whether the online monitor is scoring a sample of fresh logged traffic with this judge. online_percent: type: integer description: >- Percent of eligible fresh traffic the online monitor samples — deterministic, never double-judging a request. drift_status: type: string enum: - ok - flagged description: >- flagged = the judge may have drifted on live traffic (stale calibration or an anomalous corrected-quality drop); re-calibrate on fresh grades. online_cap_usd: type: number description: >- Weekly online-judging spend ceiling in USD (0 = uncapped). Reaching it pauses this criterion's online scoring until the week rolls over. online_spent_usd: type: number description: Online judging spend in the current weekly window. drift_signal: type: - string - 'null' description: >- Which signal raised the flag: "stale" (calibration aged out) or "quality_drop" (live corrected rate fell below what the judge validated at). Null when drift_status is ok. enum: - stale - quality_drop - null drift_reason: type: - string - 'null' description: Human-readable receipt behind a flagged drift_status. drift_checked_at: type: - string - 'null' description: >- When the drift sweep last examined this judge; null for a judge it has never reached. Error: type: object properties: error: type: object properties: message: type: string type: type: string description: >- invalid_request_error, insufficient_quota, rate_limit_error, or api_error. code: type: string description: >- Machine-stable cause, e.g. invalid_api_key, not_found, insufficient_permissions, precondition_failed. required: - message - type - code description: >- Every refusal — gateway and management API alike — uses this one envelope. responses: BadRequest: description: Malformed request or invalid field. content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: Missing, malformed, or revoked API key. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Invalid API key type: invalid_request_error code: invalid_api_key Forbidden: description: The key lacks the required owner/admin permission. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer description: >- Your workspace API key, e.g. `sk_sovereign_...`, sent as `Authorization: Bearer `. ````