> ## Documentation Index > Fetch the complete documentation index at: https://docs.querying.ai/llms.txt > Use this file to discover all available pages before exploring further. # Obtenir une réponse notée > Lisez la réponse conservée et les sources derrière un résultat noté. ## OpenAPI ````yaml GET /v1/monitors/{id}/answers/{taskId} openapi: 3.1.0 info: title: querying.ai description: >- One API for every AI answer engine. Every task is asynchronous: submit, then collect the result via webhook or polling. version: 1.0.0 servers: - url: https://api.querying.ai description: Production security: - bearerAuth: [] paths: /v1/monitors/{id}/answers/{taskId}: get: tags: - Monitors summary: Get one answer description: >- The retained evidence behind one scored cell: the answer as the engine gave it (markdown when available, capped at 8,000 characters with a trailing ellipsis when it was cut), the citations in the engine's order, the competitor names scored against it, and the aliases that were matched so the mention can be checked rather than trusted. display adds the original task's display fields (the full answer, sources, layout, places and products) while the task is still stored. Rows scored before scoring context was stored return scoringKnown false with the monitor's current aliases and a null evidenceTruncated, and answerText is null when the engine returned no answer text. operationId: getMonitorAnswer parameters: - name: id in: path required: true schema: type: string - name: taskId in: path required: true schema: type: string description: >- A taskId from cells[], results[].taskId, sources[].evidenceTaskId or the CSV. responses: '200': description: The scored answer and the definition it was scored against. content: application/json: schema: $ref: '#/components/schemas/MonitorAnswerResponse' '401': $ref: '#/components/responses/Unauthorized' '404': description: >- No monitor with that id, or no scored answer with that task id on this monitor. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: MonitorAnswerResponse: type: object properties: success: type: boolean const: true data: type: object properties: answer: $ref: '#/components/schemas/MonitorAnswerRow' display: type: - object - 'null' description: >- Display fields of the original task response, read back from the task rather than from the 8,000-character scored excerpt. Only the fields the engine returned are present: markdown, text, sources, searchQueries, layout, map, products, shoppingCards, inlineProducts, citationPills, videos and sponsored, with a Google AI Overview's under aioverview. null once the task is no longer stored, or when it carries none of these fields. mode: type: string enum: - BRAND - CATEGORY description: >- The monitor's mode. On a CATEGORY monitor aliases is empty and competitors is the whole list of brands the report ranks. aliases: type: array items: type: string description: >- The aliases this row was scored with when that is known, otherwise the monitor's current aliases. The reader needs them to see what matched. competitors: type: array items: $ref: '#/components/schemas/MonitorCompetitor' scoringKnown: type: boolean description: >- False when this row predates stored scoring context; the answer is intact but the definition shown is the monitor's current one. evidenceTruncated: type: - boolean - 'null' description: null when scoringKnown is false. ErrorResponse: type: object required: - success - error properties: success: type: boolean const: false error: $ref: '#/components/schemas/ErrorDetail' MonitorAnswerRow: type: object properties: taskId: type: string engine: $ref: '#/components/schemas/MonitorEngine' prompt: type: string mentioned: type: boolean cited: type: boolean position: type: - integer - 'null' description: >- Character offset of the earliest alias hit, or null when the brand was absent. ranAt: type: string format: date-time answerText: type: - string - 'null' description: >- At most 8,000 characters, cut with a trailing ellipsis; null when the engine returned no answer text. sources: type: array items: $ref: '#/components/schemas/MonitorStoredSource' competitorHits: type: array items: type: string scoringContext: $ref: '#/components/schemas/MonitorScoringContext' analysis: oneOf: - $ref: '#/components/schemas/AnswerAnalysis' - type: 'null' description: The task's analysis when the monitor asked for it; null otherwise. MonitorCompetitor: type: object description: >- A brand scored alongside yours in the same answers. The name is always one of its own aliases, so a bare name matches reliably. required: - name properties: name: type: string maxLength: 80 description: __you__ is reserved for your own brand. aliases: type: array maxItems: 20 items: type: string description: Other spellings of the same brand. The name is added automatically. source: type: string enum: - user - auto readOnly: true description: >- user: you added it. auto: the weekly competitor read found it in the monitor's own answers. Entries you send with source auto are ignored, so a monitor read and written back keeps its found competitors. domain: type: string readOnly: true description: The competitor's site, when the competitor read found one. ErrorDetail: type: object required: - code - message properties: code: type: string description: Stable, safe to branch on. See the Errors guide for the full list. message: type: string description: For humans. May change. details: description: >- Context for the error. An array of `{field, message}` on most `VALIDATION_ERROR`s; an object elsewhere (for example `{id}` on `RESOURCE_NOT_FOUND`, `retryAfterSec` on 429 and 503 codes). Omitted when there is nothing to add. oneOf: - type: array items: type: object properties: field: type: string message: type: string - type: object additionalProperties: true timestamp: type: string format: date-time MonitorEngine: type: string description: >- An engine a monitor can schedule: the prompt surfaces sold to customers plus the deprecated NAVER alias. GOOGLE_AIO and GOOGLE_AIMODE are accepted as input aliases and echoed as GOOGLE and AIMODE. CITATION_ANALYSIS is an analysis task, not a prompt surface, and cannot be scheduled on a monitor. enum: - CHATGPT - GEMINI - PERPLEXITY - GOOGLE - AIMODE - NAVER_AI_BRIEF - NAVER_AI_TAB - NAVER MonitorStoredSource: type: object description: >- One citation as the engine gave it. The order is the engine's, and the list is deduplicated by URL. properties: url: type: string label: type: - string - 'null' position: type: integer description: >- 1-based place in the engine's citation list. It is not a ranking of your brand. MonitorScoringContext: type: - object - 'null' description: >- The definition this answer was scored with, stored at completion. null on rows scored before this was recorded - they are the reason a comparison can be withheld as legacy_scoring_unknown. properties: aliases: type: array items: type: string domains: type: array items: type: string competitors: type: array items: $ref: '#/components/schemas/MonitorCompetitor' country: type: string version: type: string description: >- Stable hash of the definition above. Two rows with the same version are comparable; a different one means the question changed. scoredAt: type: string format: date-time answerPresent: type: boolean description: False for a completed observation whose answer was empty. evidenceTruncated: type: boolean description: True when the retained answer text was cut at the character limit. AnswerAnalysis: type: object description: >- The `analysis` field of an answer task with `include.analysis`. Brand names, the requested-brand match, recommendation and sentiment are a model's judgment; positions, ranks and source kinds are computed by rules. See the Engines guide, Answer analysis. required: - version - status properties: version: type: integer enum: - 1 status: type: string enum: - ok - no_answer - failed description: >- `no_answer`: the engine completed without answer text, nothing is mentioned and the analysis is not charged. `failed`: the analysis could not run; the task still completes and only the engine price is charged. error: type: string enum: - ANALYSIS_FAILED - ANALYSIS_TIMEOUT - ANALYSIS_UNAVAILABLE description: Present when `status` is `failed`. brands: type: array description: >- Every brand the answer names, in the order it first names each one. A product counts for its maker. items: type: object properties: name: type: string description: >- The name you sent, or for any other brand its own name, the same in every language. domain: type: - string - 'null' description: >- The brand's site: the first of the domains you sent, or the one found for it. writtenAs: type: string description: >- The brand's name as the answer first writes it: the first of `spellings`. spellings: type: array items: type: string description: >- Every way the answer writes the brand's name, in the order it first uses each. A product or description written after the name is not part of a spelling. rank: type: integer minimum: 1 role: type: - string - 'null' enum: - brand - competitor - null recommended: type: - boolean - 'null' description: >- Null when the name matched but the model did not read it as a brand in this answer. sentiment: type: - string - 'null' enum: - positive - neutral - negative - null sentimentScore: type: - number - 'null' enum: - 0.9 - 0.5 - 0 - -0.5 - -0.9 - null targets: type: array description: The `brand` and `competitors` you sent, in your order. items: type: object properties: name: type: string role: type: string enum: - brand - competitor mentioned: type: boolean rank: type: - integer - 'null' recommended: type: - boolean - 'null' sentiment: type: - string - 'null' enum: - positive - neutral - negative - null sentimentScore: type: - number - 'null' cited: type: boolean description: >- A citation is on one of its domains. False when no domains were sent. sources: type: array description: The answer's citations in the engine's order. items: type: object properties: position: type: integer minimum: 1 url: type: string domain: type: - string - 'null' kind: type: string enum: - owned - competitor - editorial - review_media - pr_wire - institution - reviews - commerce - social - blog - community - video - brand - content - other brand: type: - string - 'null' description: The brand whose domain this is, for `owned` and `competitor`. responses: Unauthorized: description: Missing or invalid bearer token. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: success: false error: code: MISSING_API_KEY message: Missing or invalid API key timestamp: '2026-07-09T04:12:00.000Z' securitySchemes: bearerAuth: type: http scheme: bearer description: 'Your API key, sent as `Authorization: Bearer `.' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.