Trace a completed answer with just its task ID

Send the taskId of a completed answer to Source Influence, and it reads the answer and its citations for you.

What changed

• One field, taskId, is the whole request when the answer came from querying.ai.
• The answer Markdown, the cited URLs in the engine’s order, the prompt, the country and the engine all come from the task itself.
• The analysis takes the first 100 cited URLs, with up to 10 discussion threads among them.

How it works

Any completed answer task of yours that GET /v1/async/task/{id} still returns can be traced by its ID alone. Source Influence takes the answer’s Markdown, or its text when the engine returned plain text, and the URLs it cited, in the order the engine listed them.

The analysis covers citations that lead to real pages, so product cards, video cards and Google search links are skipped.

Where it helps

• Trace the answers your scheduled jobs already collected, one ID at a time.
• Build a pipeline that runs answer tasks and traces each one as soon as it completes.

Send a request

Send the request with your API key in the Authorization header.

curl -X POST https://api.querying.ai/v1/source-influence \
  -H "Authorization: Bearer $QUERYING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskId": "e5aba119-a26e-4f82-a965-35c9234a428b" }'

Request fields

taskIdstringRequired

A completed answer task of yours. Its answer and cited pages become answer and citations.

countrystring

Country the cited pages are read from. Default US.

webhook.urlstring

An HTTPS address on your server. The finished task is posted there the moment it completes.

idempotencyKeystring

Your own ID for the request. Each key creates one task per account, so a retried send stays a single task.

Response

A finished task looks like this, trimmed for length.

{
  "success": true,
  "task": {
    "id": "1d0521d6-26fe-4fbf-9e54-3a97c0e566a3",
    "taskType": "SOURCE_INFLUENCE",
    "status": "COMPLETED",
    "createdAt": "2026-10-02T15:44:12.823Z"
  },
  "credits": { "creditsToCharge": 133, "creditsCharged": 133 },
  "response": {
    "answer": "Here are several **nearby cafés that look particularly suitable for laptop work**, based on current local listings and work-friendly details:\n…",
    "sources": [
      {
        "id": "s0",
        "url": "https://awifiplace.com/cities/new-york",
        "paragraphs": [
          {
            "id": "s0p4",
            "text": "100 Cafés to Work in New York\n\nCarefully curated from Google reviews: All locations offer WiFi and are verified as laptop-friendly by remote …"
          }
        ]
      }
    ],
    "links": [
      {
        "id": "l0",
        "paragraphId": "s0p4",
        "answerRanges": [
          { "start": 0, "end": 141 },
          { "start": 179, "end": 247 },
          { "start": 248, "end": 288 },
          { "start": 869, "end": 938 }
        ],
        "explanation": "The page describes 100 New York cafés as offering WiFi and verified as laptop-friendly by remote workers, supporting their suitability for laptop work and Wi-Fi use."
      }
    ],
    "insights": [
      {
        "summary": "The recommendations are best read as promising laptop-work options, not guaranteed workspaces: the underlying guides rely on reported Wi‑Fi and work-friendly listings, while noting that connection quality, outlets, and seating can vary.",
        "linkIds": ["l0", "l2", "l3", "l4", "l6", "l7", "l8"]
      }
    ]
  }
}

task.statusstring

QUEUED, PROCESSING, then COMPLETED with the answer or FAILED with error.

credits.creditsChargedinteger

Credits charged for the finished task. A failed task charges 0.

response.answerstring

The answer you sent, unchanged. Ranges are UTF-16 offsets into this exact text.

response.sourcesarray

One entry per cited page, with its url and the paragraphs in the result, each with an id and text.

response.linksarray

Each link pairs one paragraph with the answerRanges it matches and a one-sentence explanation.

response.insightsarray

Short summaries of what the links add up to, each naming the links behind it in linkIds.

Receive the result

The request returns the task right away with status QUEUED. Poll GET /v1/async/task/{id} until status is COMPLETED or FAILED, or add webhook.url and the finished task arrives at your server with the same task, credits and response. Results stay available for 24 hours after a task finishes.

curl https://api.querying.ai/v1/async/task/$TASK_ID \
  -H "Authorization: Bearer $QUERYING_API_KEY"

Pricing

Pricing stays the same: credits are held when the analysis starts and settled when it finishes.