AimRank Judge Prompt Synthesis API
The Judge Prompt Synthesis API from AimRank — 9 operation(s) for judge prompt synthesis.
The Judge Prompt Synthesis API from AimRank — 9 operation(s) for judge prompt synthesis.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/aimrank-io:aimrank-io-judge-prompt-synthesis-api"
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: AimRank Judge Prompt Synthesis API
description: Ranking-as-a-Service API — Turn binary comparisons into calibrated rankings with Glicko-2, Bradley-Terry, TrueSkill, and cross-domain transfer learning. Includes webhooks, API keys, RLHF exports, and embeddable widgets.
version: 4.12.0
tags:
- name: Judge Prompt Synthesis
paths:
/api/v1/rankings/{ranking_id}/synthesize-judge:
post:
tags:
- Judge Prompt Synthesis
summary: Post Synthesize Judge
description: 'Synthesise an LLM-judge prompt from this ranking''s human votes.
Tier-gated: synthesis uses the same Bedrock budget as a judge vote
(one Bedrock call per synthesis).'
operationId: post_synthesize_judge_api_v1_rankings__ranking_id__synthesize_judge_post
parameters:
- name: ranking_id
in: path
required: true
schema:
type: string
title: Ranking Id
requestBody:
content:
application/json:
schema:
anyOf:
- $ref: '#/components/schemas/SynthesizeRequest'
- type: 'null'
title: Body
responses:
'201':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/rankings/{ranking_id}/judge-prompts:
get:
tags:
- Judge Prompt Synthesis
summary: List Judge Prompts
description: List judge-prompt artifacts for a ranking. Owner-only.
operationId: list_judge_prompts_api_v1_rankings__ranking_id__judge_prompts_get
parameters:
- name: ranking_id
in: path
required: true
schema:
type: string
title: Ranking Id
- name: include_inactive
in: query
required: false
schema:
type: boolean
default: false
title: Include Inactive
- name: limit
in: query
required: false
schema:
type: integer
default: 50
title: Limit
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/judge-prompts/public:
get:
tags:
- Judge Prompt Synthesis
summary: List Public Judges
description: 'Discover public judge prompts. No auth required.
Filters:
- ``category``: match the ranking''s category (free-text)
- ``domain_id``: match the ranking''s domain (when set)
Sort options: ``fork_count`` (default — most-forked first),
``recent`` (most-recently-generated first), ``faithfulness``
(highest synthesiser self-rating first).'
operationId: list_public_judges_api_v1_judge_prompts_public_get
parameters:
- name: category
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Category
- name: domain_id
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Domain Id
- name: limit
in: query
required: false
schema:
type: integer
default: 50
title: Limit
- name: sort
in: query
required: false
schema:
type: string
default: fork_count
title: Sort
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/judge-prompts/{prompt_id}:
get:
tags:
- Judge Prompt Synthesis
summary: Get Judge Prompt
description: Read a single judge-prompt artifact (including the full text).
operationId: get_judge_prompt_api_v1_judge_prompts__prompt_id__get
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
title: Prompt Id
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
delete:
tags:
- Judge Prompt Synthesis
summary: Deactivate Judge Prompt
description: 'Soft-delete a judge-prompt artifact (sets is_active=''deleted'').
Hard-delete is intentionally not exposed — artifacts are Annex IV
evidence; preserve the audit trail.'
operationId: deactivate_judge_prompt_api_v1_judge_prompts__prompt_id__delete
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
title: Prompt Id
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/judge-prompts/{prompt_id}/visibility:
patch:
tags:
- Judge Prompt Synthesis
summary: Set Visibility
description: 'Set the visibility of an artifact — owner-only.
- ``private``: owner only (default for newly-synthesised artifacts)
- ``unlisted``: anyone with the URL can view + fork
- ``public``: discoverable in `GET /judge-prompts/public`'
operationId: set_visibility_api_v1_judge_prompts__prompt_id__visibility_patch
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
title: Prompt Id
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/VisibilityUpdate'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/judge-prompts/{prompt_id}/fork:
post:
tags:
- Judge Prompt Synthesis
summary: Fork Judge Prompt
description: 'Clone a public/unlisted artifact into the caller''s account.
The source must be public or unlisted (the caller must have been
able to discover or be handed the URL). Forking carries the prompt
text and suggested model forward; provenance metadata is regenerated
with ``forked_from_id`` so the audit trail links back to the source.
``target_ranking_id`` is optional — when set, the fork attaches to
that ranking (which must be owned by the caller). When omitted, the
fork attaches to the SOURCE ranking only if the caller also owns
that ranking; otherwise the call requires ``target_ranking_id``.'
operationId: fork_judge_prompt_api_v1_judge_prompts__prompt_id__fork_post
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
title: Prompt Id
- name: target_ranking_id
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Target Ranking Id
responses:
'201':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/judge-prompts/{prompt_id}/validate:
post:
tags:
- Judge Prompt Synthesis
summary: Post Validate Judge Prompt
description: 'Score a synthesised judge against its source ranking''s human votes.
Owner-only (the validation runs N Bedrock calls — only the artifact
owner gets to spend the quota). Tier-gated: each pair = 1 judge-
quota unit.
Default: 30 pairs sampled with replacement from pairs where ≥60% of
humans agreed. Returns the full report with accuracy + Wilson 95%
CI + Cohen κ vs humans + per-subset breakdown + cost.'
operationId: post_validate_judge_prompt_api_v1_judge_prompts__prompt_id__validate_post
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
title: Prompt Id
requestBody:
content:
application/json:
schema:
anyOf:
- $ref: '#/components/schemas/ValidateRequest'
- type: 'null'
title: Body
responses:
'201':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/judge-prompts/{prompt_id}/validations:
get:
tags:
- Judge Prompt Synthesis
summary: List Validations
description: 'List validation reports for a judge-prompt artifact.
Owner-only — but the artifact''s owner is the SOURCE owner, not the
forker. Forks have their own validation runs.'
operationId: list_validations_api_v1_judge_prompts__prompt_id__validations_get
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
title: Prompt Id
- name: limit
in: query
required: false
schema:
type: integer
default: 50
title: Limit
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/judge-validations/{validation_id}:
get:
tags:
- Judge Prompt Synthesis
summary: Get Validation
description: 'Read a single validation report (includes per-pair detail).
Owner-only check via the parent artifact.'
operationId: get_validation_api_v1_judge_validations__validation_id__get
parameters:
- name: validation_id
in: path
required: true
schema:
type: string
title: Validation Id
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
components:
schemas:
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
VisibilityUpdate:
properties:
visibility:
type: string
pattern: ^(private|unlisted|public)$
title: Visibility
type: object
required:
- visibility
title: VisibilityUpdate
SynthesizeRequest:
properties:
synthesis_model_id:
anyOf:
- type: string
maxLength: 200
- type: 'null'
title: Synthesis Model Id
description: Bedrock model ID for the synthesis call. Defaults to Claude Opus.
random_seed:
type: integer
maximum: 2147483647.0
minimum: 0.0
title: Random Seed
description: Seed for example-pair sampling — for reproducibility.
default: 42
type: object
title: SynthesizeRequest
ValidateRequest:
properties:
n_pairs:
type: integer
maximum: 200.0
minimum: 2.0
title: N Pairs
default: 30
judge_model_id:
anyOf:
- type: string
maxLength: 200
- type: 'null'
title: Judge Model Id
random_seed:
type: integer
maximum: 2147483647.0
minimum: 0.0
title: Random Seed
default: 42
validation_ranking_id:
anyOf:
- type: string
maxLength: 36
- type: 'null'
title: Validation Ranking Id
description: Optional override — validate the prompt against a DIFFERENT ranking's human votes (transfer test). Defaults to the artifact's source ranking.
type: object
title: ValidateRequest
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
securitySchemes:
APIKeyHeader:
type: apiKey
in: header
name: X-API-Key