---
name: research-ai-prompts
description: "Find the questions people ask AI assistants about a topic in South Korea or the United States, ranked by the monthly search demand behind each one, with intent, funnel stage, sub-topic, audience and the brands searched in the same space. Use it to choose the prompts a GEO monitor should track. 11 credits per research."
---

# Research AI prompts with querying.ai

Prompt research turns one topic into the questions people ask AI assistants, ordered by how many people search for that need each month, and picks the set a monitor should track.

Send `Authorization: Bearer $QUERYING_API_KEY` on every request to https://api.querying.ai. Getting a key, and the 500 credits a new account starts with: https://querying.ai/auth.md

## Submit

```bash
curl -X POST https://api.querying.ai/v1/prompt-research \
  -H "Authorization: Bearer $QUERYING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"seed": "sunscreen", "country": "US", "limit": 20, "brand": "Acme", "brandDescription": "Mineral sunscreen for sensitive skin"}'
```

- `seed`: a short product or category term, 1-30 characters.
- `country`: `KR` (questions in Korean) or `US` (English).
- `limit`: 1-50 questions, default 20. `exclude[]` drops subtopics; `brand` keeps your own name out of the questions.
- `brandDescription`: adds a `fit` to each question so `monitorSet` favors the ones your brand answers.

## Read the result

Tasks run asynchronously. The POST returns `task.id` with `status` `QUEUED`. Poll `GET /v1/async/task/{id}` every few seconds until `task.status` is `COMPLETED` or `FAILED`, or add `"webhook": {"url": "https://your.server/hook"}` to the request and the finished task arrives at that URL as a POST. A finished task stays readable for 24 hours. Research usually completes in 30-60 seconds and reports `taskType` `PROMPT_RESEARCH`.

In `response`:

- `prompts[]`: `prompt`, `monthlySearchVolume`, `demandShare`, `intent` (informational, commercial, transactional), `funnelStage`, `topic`, `persona` and `brandMentions`.
- `monitorSet.prompts[]`: the questions to add to a monitor, in `rank` order.
- `topics[]`, `personas[]` and `brands[]`: demand summed by sub-topic, by audience and by brand.

Pass `monitorSet.prompts[].prompt` as the `prompts` of `POST /v1/monitors` (the track-ai-visibility skill).

## Errors

| HTTP | `code` | When |
| --- | --- | --- |
| 401 | `MISSING_API_KEY` | The key is missing, wrong, expired or revoked. |
| 402 | `INSUFFICIENT_CREDITS` | The account balance is below the task's credits. |
| 403 | `KEY_SCOPE_DENIED` | The key is limited to other engines. |
| 422 | `REGION_UNSUPPORTED` | The engine serves other countries; pick another engine or country. |
| 429 | `KEY_DAILY_CREDIT_LIMIT` | The key reached its daily credit limit; `details.retryAfterSec` counts down to the next UTC day. |

## Over MCP

`research_prompts` on https://mcp.querying.ai/mcp submits and waits for the result.

Reference: https://docs.querying.ai/research/prompt-research