AI referral traffic report

See which known AI assistants sent visits recorded by Google Analytics and where those visitors landed. It measures observed referrals, not general visibility inside an assistant.

Install and run the report

Install the CLI once, then run seo start to connect your site and Google data. After setup you can run this report yourself or ask your agent to run it.

Runafter install

Install the SEO CLI globally.

npm i -g seo

Run setup after installation.

seo start

Find Google Analytics sessions referred by known AI products.

seo ai-referrals --project example

What you get from this report

Find visits from known AI assistants in Google Analytics, see which landing pages received them and keep missing referrers separate from confirmed traffic.

Best for: You need observed referral evidence rather than an AI visibility estimate.
Needs: Google Analytics traffic acquisition rows
You get: Find visits from known AI assistants in Google Analytics, see which landing pages received them and keep missing referrers separate from confirmed traffic.
Use next: Find opportunities for one page

Every report follows the same rules for missing data and outside estimates.See how report data works.

What you need before you run it

The report uses the information below. Optional sources are only used when you ask for them.

Google Analytics traffic acquisition rows

Provides session source, landing page, sessions, engagement, and the selected date scope.

Documented AI referral source rules

Defines which returned source values are included in the AI referral result.

Use a different report for these jobs

These jobs need a different report or a manual review.

You want to know whether important pages are technically available to AI search systems, regardless of whether Google Analytics recorded a visit.

Run AI readiness. It checks crawl, index, snippet, and page-structure evidence that referral analytics cannot see.

AI search readiness audit

You need to know whether assistants mention or cite the site even when nobody clicks through.

Run AI mention research for provider-indexed mentions, questions, and cited URLs. Use fixed prompt observations when you need a current answer. AI referrals can only confirm visits that reached Google Analytics with a recognisable source.

AI mention research report

Use the report with an agent or in code

The command above is enough for most work. These options let an agent, script or application run the same report with explicit input and structured output.

Use the report catalog when an agent, script or CI job needs predictable JSON instead of the normal terminal output. Check the current input first, then run the report with the validated parameters.

Check the current input before the agent or script runs the report.

seo reports describe ai-referrals --json

Once the input is valid, run the report through the report catalog.

seo reports run ai-referrals --params '{"property":"123456789","startDate":"28daysAgo","endDate":"yesterday","resultLimit":25}' --json

An MCP agent follows the same two-step flow. It inspects the current schema, fills the required fields and only then runs the report.

Ask the MCP server for the current report input.

{
  "id": "ai-referrals"
}

Run the report after the agent has checked and filled the input.

{
  "id": "ai-referrals",
  "params": {
    "property": "123456789",
    "startDate": "28daysAgo",
    "endDate": "yesterday",
    "resultLimit": 25
  }
}

Install the package in a Node 22 project when your application needs to run the report directly. The result includes the same evidence, warnings and limits returned through the CLI and MCP server.

Add the SEO package to your project.

npm install seo

Run the report from your TypeScript application.

import { executeReport } from 'seo/mcp'

const result = await executeReport(
  'ai-referrals',
  {
  "property": "123456789",
  "startDate": "28daysAgo",
  "endDate": "yesterday",
  "resultLimit": 25
},
)

console.log(result)

What to do next

Check the matched referrer and landing page before treating a session as useful AI traffic. Search demand and assistant visibility need their own reports because Google Analytics only records visits that reached the site.

01Inspect the landing pages receiving useful referral traffic.
02Use a stable prompt corpus if you separately monitor citations or answers.

Compare one URL with its Search Console queries and live page evidence to find focused content, CTR and coverage opportunities before rewriting the page.

Page SEO opportunities

Turn real Search Console queries into repeatable AI monitoring prompts so assistant answers can be checked against demand your site already sees.

AI search query report

Check whether crawlers can access and use important pages in AI search. Find technical blockers without inventing a visibility or citation score.