Get a criterion

curl --request GET \
  --url https://gateway.omnia-voice.com/v1/criteria/{id} \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://gateway.omnia-voice.com/v1/criteria/{id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://gateway.omnia-voice.com/v1/criteria/{id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://gateway.omnia-voice.com/v1/criteria/{id}"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://gateway.omnia-voice.com/v1/criteria/{id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "name": "Complete final answer",
  "description": "<string>",
  "judge_prompt": "<string>",
  "judge_model": "<string>",
  "status": "draft",
  "source": "human",
  "tier": "aligned",
  "trust": "trustworthy",
  "tpr_ci": "<unknown>",
  "tnr_ci": "<unknown>",
  "fail_grades_needed": "<unknown>",
  "pass_grades_needed": 123,
  "tpr": 123,
  "tnr": 123,
  "kappa": 123,
  "alignment_n": 123,
  "aligned_at": "2023-11-07T05:31:56Z",
  "created_at": "2023-11-07T05:31:56Z",
  "unit": "request",
  "population": "<string>",
  "population_family": "<string>",
  "online_enabled": true,
  "online_percent": 123,
  "drift_status": "ok",
  "online_cap_usd": 123,
  "online_spent_usd": 123,
  "drift_signal": "stale",
  "drift_reason": "<string>",
  "drift_checked_at": "<string>"
}

GET

criteria

{id}

Get a criterion

curl --request GET \
  --url https://gateway.omnia-voice.com/v1/criteria/{id} \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://gateway.omnia-voice.com/v1/criteria/{id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://gateway.omnia-voice.com/v1/criteria/{id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://gateway.omnia-voice.com/v1/criteria/{id}"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://gateway.omnia-voice.com/v1/criteria/{id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "name": "Complete final answer",
  "description": "<string>",
  "judge_prompt": "<string>",
  "judge_model": "<string>",
  "status": "draft",
  "source": "human",
  "tier": "aligned",
  "trust": "trustworthy",
  "tpr_ci": "<unknown>",
  "tnr_ci": "<unknown>",
  "fail_grades_needed": "<unknown>",
  "pass_grades_needed": 123,
  "tpr": 123,
  "tnr": 123,
  "kappa": 123,
  "alignment_n": 123,
  "aligned_at": "2023-11-07T05:31:56Z",
  "created_at": "2023-11-07T05:31:56Z",
  "unit": "request",
  "population": "<string>",
  "population_family": "<string>",
  "online_enabled": true,
  "online_percent": 123,
  "drift_status": "ok",
  "online_cap_usd": 123,
  "online_spent_usd": 123,
  "drift_signal": "stale",
  "drift_reason": "<string>",
  "drift_checked_at": "<string>"
}

Authorizations

Authorization

string

header

required

Your workspace API key, e.g. sk_sovereign_..., sent as Authorization: Bearer <key>.

Path Parameters

string

required

Response

The criterion

string

name

string

Example:

"Complete final answer"

description

string | null

judge_prompt

string

The binary instruction the judge applies. State precisely what makes a response FAIL.

judge_model

string

status

enum<string>

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.

Available options:

draft,

retired

source

enum<string>

Available options:

human,

assist_suggested

tier

enum<string>

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.

Available options:

aligned,

weak,

misaligned,

unmeasured

trust

enum<string>

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.

Available options:

trustworthy,

under-measured,

borderline,

misaligned,

unmeasured

tpr_ci

array | null

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

array | null

95% Wilson interval [low, high] for tnr. Null when no human-passed grades exist.

fail_grades_needed

integer | null

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

integer | null

The same for TNR, measured only on human-passed rows.

tpr

number | null

P(judge says fail | you said fail) — how often it catches real failures.

tnr

number | null

P(judge says pass | you said pass).

kappa

number | null

Cohen's κ — chance-corrected agreement (raw agreement is inflated by class imbalance).

alignment_n

integer | null

aligned_at

string<date-time> | null

created_at

string<date-time>

unit

enum<string>

What this judge grades: one exchange, or a whole agent run / trace-grouped conversation. Fixed at creation.

Available options:

request,

trace

population

string

The tag this criterion judges online AND aligns against ('' = all logged traffic). Changing it voids alignment.

population_family

string

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

boolean

Whether the online monitor is scoring a sample of fresh logged traffic with this judge.

online_percent

integer

Percent of eligible fresh traffic the online monitor samples — deterministic, never double-judging a request.

drift_status

enum<string>

flagged = the judge may have drifted on live traffic (stale calibration or an anomalous corrected-quality drop); re-calibrate on fresh grades.

Available options:

ok,

flagged

online_cap_usd

number

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

number

Online judging spend in the current weekly window.

drift_signal

enum<string> | null

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.

Available options:

stale,

quality_drop,

null

drift_reason

string | null

Human-readable receipt behind a flagged drift_status.

drift_checked_at

string | null

When the drift sweep last examined this judge; null for a judge it has never reached.

Overview

Inference API

Capture & setup API

Logs & datasets API

Grades (labels) API

Judges (criteria) API

Evals API

Fine-tuning API

Reinforcement learning API

Dedicated endpoints API

Model aliases API

Model versions API

Get a criterion

Authorizations

Path Parameters

Response