AI search query report built from real SEO query demand.

Run this report from the CLI, an MCP client, or application code. Every surface uses the same report definition and returns the same evidence. JSON is the source of truth; Markdown makes it readable without hiding dates, limits, warnings, or skipped work.

What this report helps you decide

Which reproducible prompts can be derived from the searches already associated with this site?

• You need a limited prompt corpus whose source queries and dates remain attached.
• Repeatable templates matter more than creative prompt generation.

Command facts

Report id

seo-to-ai-query

Execution

Local process

Outputs

JSON and Markdown

Example parameters

site, days, limit, minImpressions, maxRows

Agent discovery

seo reports describe seo-to-ai-query --json

Interactive prompts

Human CLI commands only

When this report is not the right tool

These cases need a different report, more evidence, or a human decision. Do not force this report to answer a question its data cannot support.

• You want to know whether AI assistants already send visits recorded by your analytics property. Recommended report: Find AI referral traffic. Run AI referrals. It reads captured GA4 referral traffic and reports the sources, landing pages, sessions, and available engagement evidence. Generated monitoring prompts contain no referral or visit data.
• You need to know whether an assistant currently mentions, cites, or recommends the site for a prompt. No automated report in this package tests live assistant answers. Run the generated prompt set against the chosen assistants under a documented location, account, model, and date, then save the responses for comparison. This report supplies repeatable prompts and their Search Console source evidence.

Data sources and inputs

• Returned Search Console queries. Provides the source wording, impressions, dates, and property scope behind each prompt.
• Prompt and source row limits. Bound the eligible query set and final monitoring corpus.

What this report checks

• Finds source queries with enough impressions to meet the configured threshold.
• Identifies question, comparison, local, and decision-making intent where the wording supports it.
• Applies stable prompt templates and preserves the source query, metrics, date range, and completeness beside each result.

How it works

• Applies stable prompt templates to eligible source queries, preserves source completeness, and bounds both retrieval and output.

The JSON result keeps dates, thresholds, limits, skipped work, and source completeness beside the finding. Missing, partial, capped, filtered, and complete data remain different states.

Run the report from the CLI

Turn returned searches into repeatable AI monitoring prompts. Agents and CI should inspect the live schema before their first run.

seo seo-to-ai-query --project example

seo reports describe seo-to-ai-query --json

seo reports run seo-to-ai-query --params '{"site":"sc-domain:example.com","days":90,"limit":20,"minImpressions":100,"maxRows":10000}' --json

Project profiles can fill supported property and analytics inputs for the human-facing commands. The catalog form shown here is explicit by design, so agents and CI jobs do not prompt or guess.

How an MCP agent should use it

Call seo_describe_report first so the agent sees when this report is useful and gets the current input schema. Then callseo_run_report with the validated parameters. Read the status, warnings, source limits, and skipped sections before acting on a finding.

{
  "id": "seo-to-ai-query"
}

{
  "id": "seo-to-ai-query",
  "params": {
    "site": "sc-domain:example.com",
    "days": 90,
    "limit": 20,
    "minImpressions": 100,
    "maxRows": 10000
  }
}

Use a follow-up report returned by the result instead of guessing the next tool. The local MCP server and CLI use the same report definition and evidence. Their outer transport envelopes differ.

Use the report in a TypeScript app

Install seo as a project dependency, then call the same report catalog used by the CLI and MCP. executeReportrejects an unknown report id or invalid parameters. Provider and runtime failures come back as structured results withisError set.

npm install seo

import { executeReport } from 'seo/mcp'

const result = await executeReport(
  'seo-to-ai-query',
  {
  "site": "sc-domain:example.com",
  "days": 90,
  "limit": 20,
  "minImpressions": 100,
  "maxRows": 10000
},
)

console.log(result)

The TypeScript library guide also covers direct core functions, schema discovery, and the difference betweenexecuteReport and runReport.

What comes back and how to read it

• A repeatable prompt seed set with its source queries, metrics, templates, and stable ordering.
• Selection source details and caveats that stop generated prompts being mistaken for AI demand, citations, or traffic forecasts.
• Use the prompts as monitoring inputs. Store each source query and date range beside later observations so the corpus remains auditable.

Start with dataStatus, source details, warnings, and caveats. Then inspect the observed evidence before derived findings or suggested actions.

What this report cannot tell you

• Generated prompts are not observed AI demand, citation evidence, or traffic estimates.

What to do next

1. Choose representative variants and monitor them on a controlled schedule.
2. Use AI referrals separately for observed GA4 referral evidence.

Related reports

• Find AI referral traffic. See which known AI products sent referral sessions recorded by GA4 and which landing pages received them.
• Find community and comparison searches. Surface searches containing explicit review, comparison, forum, recommendation, or first-hand experience wording.
• Check AI search technical readiness. Review crawl access, indexability, snippet controls, page structure, and optional agent resources without inventing an AI visibility score.

Sources behind the guidance

These primary sources define the provider data or search controls used in the interpretation above.

• Search Console Search Analytics API guidance
• Google guidance for AI features and websites

Browse all reports in AI search evidence.