AI Visibility Report Generator

AI Visibility Report Generator

Turn raw AI visibility checks into a client-ready report in one run.

This Actor takes records from AI Brand Visibility Monitor or inline visibility-check JSON and generates a structured report with scorecards, brand mention rate, citation coverage, competitor mentions, priority gaps, and recommended next actions.

Use it when an agency, GEO/AEO consultant, SEO team, or B2B marketer needs a weekly or monthly AI visibility report they can send to a client instead of cleaning up raw dataset rows by hand.

The fastest first run is to paste the example input, run the Actor, and open REPORT.md in the run's key-value store. After that, replace the sample records with your AI Brand Visibility Monitor dataset ID or your own visibility-check records.

Typical workflow:

1. Run AI Brand Visibility Monitor on buyer-intent prompts.
2. Pass the monitor dataset ID into this Actor.
3. Get one summarized dataset item plus a REPORT.md file in the key-value store.
4. Copy the report into a client email, Slack update, Google Doc, or recurring dashboard.

Workflow Hub

See the public AI visibility workflow for the monitor -> report path and links to both Actors. Agencies can start from the GEO client reporting use case. For the first proof run, use the AI Visibility Report demo script, sample REPORT.md, and proof GIF.

60-Second First Run

You can prove the report flow without an API key, a private dataset, or a production client account.

1. Leave the prefilled brandName, reportPeriod, and visibilityChecks sample in place.
2. Run the Actor once.
3. Open the dataset item to confirm scorecard fields such as averageVisibilityScore, brandMentionRate, topCompetitors, topGaps, and recommendedNextActions.
4. Open REPORT.md in the run's key-value store and paste it into a client email, Slack update, Google Doc, or weekly dashboard.

The sample uses fictional Northstar CRM records with one competitor-only answer and one partial brand-mention answer. That gives the report enough signal to show missing comparison content, citation gaps, competitor pressure, and concrete next actions.

What You Learn

• Average AI visibility score for a brand
• Brand mention rate across successful checks
• Citation/domain coverage
• Which competitors appear most often
• Which buyer queries are the biggest visibility gaps
• What actions to prioritize next

Use Cases

• Weekly GEO/AEO reports for agencies
• Monthly client reporting from AI visibility checks
• Competitive visibility summaries
• Content-priority planning
• Slack, Sheets, or dashboard summaries from Apify datasets
• Lightweight client proof that turns "we checked AI answers" into a readable deliverable

When To Use This Actor

Use this Actor after you already have AI visibility records. It does not query AI models directly. For data collection, start with AI Brand Visibility Monitor.

This separation keeps the workflow predictable:

• Monitor Actor: collects brand-query-model checks
• Report Actor: turns those checks into a readable report

Input

Provide AI Brand Visibility Monitor records inline or pass the source datasetId.

For the lowest-friction Store run, use inline visibilityChecks. For automation, pass a datasetId from AI Brand Visibility Monitor and keep the same brandName and reportPeriod fields.

{
  "brandName": "Northstar CRM",
  "reportPeriod": "May 2026",
  "visibilityChecks": [
    {
      "status": "succeeded",
      "brandMentioned": false,
      "brandDomainMentioned": false,
      "visibilityScore": 5,
      "query": "best CRM for B2B SaaS teams",
      "modelId": "openrouter/auto",
      "competitorsMentioned": ["HubSpot", "Salesforce", "Pipedrive"],
      "recommendation": "Publish comparison and alternatives content for B2B SaaS CRM buyers."
    },
    {
      "status": "succeeded",
      "brandMentioned": true,
      "brandDomainMentioned": false,
      "visibilityScore": 55,
      "query": "HubSpot alternatives for product-led sales teams",
      "modelId": "openrouter/auto",
      "competitorsMentioned": ["HubSpot"],
      "recommendation": "Strengthen canonical domain citations and publish a direct alternatives page."
    }
  ]
}

Output

The dataset contains one summarized report item, and the run writes a Markdown report for easy sharing:

{
  "status": "succeeded",
  "brandName": "Northstar CRM",
  "reportPeriod": "May 2026",
  "checksAnalyzed": 2,
  "averageVisibilityScore": 30,
  "brandMentionRate": 0.5,
  "citationRate": 0,
  "topCompetitors": [{"name": "HubSpot", "mentions": 2}],
  "recommendedNextActions": [
    "Create or refresh buyer-intent pages where Northstar CRM is absent from AI answers."
  ]
}

The run also writes REPORT.md to the key-value store for easy copying into docs, emails, or reporting workflows.

Example Report Sections

The generated markdown report includes:

• Executive summary
• Scorecard
• Recommended actions
• Top competitors
• Priority gaps

FAQ

Does this Actor query ChatGPT, Perplexity, Claude, or other AI models?

No. This Actor only turns existing visibility-check records into a report. Use AI Brand Visibility Monitor first if you need to collect AI answer visibility data.

What input do I need for the first run?

You need a brandName plus either inline visibilityChecks or a datasetId from AI Brand Visibility Monitor. The Store example uses fictional Northstar CRM records so you can test the report format without credentials or private data.

What do I get after a run?

You get one structured dataset item with summary metrics and a REPORT.md file in the key-value store. The Markdown file is designed to paste into a client email, Google Doc, Slack update, or recurring reporting workflow.

How should I automate this weekly?

Schedule AI Brand Visibility Monitor first, then run this Actor with the monitor dataset ID. Use reportPeriod to label the week or month, then route REPORT.md into your reporting destination.

How much does it cost?

The configured paid event is ai-visibility-report-generated at $0.50 per generated report. Check the live Store pricing panel before running large volumes because Apify platform pricing and account-level charges can change.

Can I use my own visibility data?

Yes. Inline records should include fields such as status, brandMentioned, visibilityScore, query, modelId, competitorsMentioned, and recommendation. Records with more context usually produce a more useful report.

Pricing

Default monetization model: pay per event.

Recommended chargeable event:

• Event name: ai-visibility-report-generated
• Event meaning: one generated AI visibility report
• Store price: $0.50 per report

This Actor is public at https://apify.com/geneius/ai-visibility-report-generator. PPE was configured before publication, and public smoke runs have recorded the expected ai-visibility-report-generated charge.

Limitations

• This Actor does not query AI models directly. Use AI Brand Visibility Monitor first.
• Report quality depends on the breadth and freshness of supplied visibility checks.
• It is best sold as a companion workflow, not as a raw standalone scraper.

Automation And Agent Use

• Schedule AI Brand Visibility Monitor weekly, then run this Actor on the resulting dataset.
• Store REPORT.md in a client folder or send it to Slack.
• Append report metrics to Google Sheets for trend tracking.
• Use topGaps and recommendedNextActions to drive content backlog planning.

Local Development

python3 -m pip install -r requirements.txt
ACTOR_TEST_PAY_PER_EVENT=true apify run --purge --input-file examples/smoke-input.json