---
title: "AI Agents Analytics Dashboard Reference | HitKeep"
description: "Read the HitKeep AI Agents dashboard reference for AI requests, crawler fetches, AI-referred visits, correlation reports, filters, and API examples."
canonical: "https://hitkeep.com/guides/analytics/ai-visibility/"
---

# AI Agents Analytics Dashboard Reference

The HitKeep **AI Agents** dashboard brings three related but separate signals together. Browser tracking captures AI-referred human visits, server-side ingest captures AI crawler fetches, and assistant instrumentation captures on-site AI activity.

1. **What AI crawlers fetch from your site**
2. **Which of those fetched pages later attract AI-referred human visits**
3. **What visitors do with an instrumented assistant**

That distinction matters. A crawler fetch is not the same thing as a human referral, and HitKeep keeps those signals separate instead of collapsing them into one number.

For the broader measurement model across rendered sessions, agent navigation, remote retrieval, and backend outcomes, read [AI Browser Tracking in 2026](https://hitkeep.com/blog/ai-browsers-web-analytics-2026/).

![HitKeep AI visibility overview with fetch KPI cards, filters, and fetch volume over time](https://hitkeep.com/_astro/analytics-ai-visibility.DPXf9_ks_Z2apQEG.webp)

Overview of the AI Agents page: fetch KPIs, assistant/operator filters, and crawl demand over time.

## What the dashboard shows

The **AI Agents** page is split into three layers:

- **Fetch analytics** with KPI cards for total fetches, unique paths, unique assistants, 4xx and 5xx rates, response time, and bytes served
- **Correlation analytics** with summary KPIs plus full-width tabbed views for citation yield, opportunity pages, and failure hotspots
- **Assistant activity** with request, referral, crawl, and pageview context plus filterable assistant events

The page supports filtering by assistant, operator family, and resource type so you can answer questions like:

- What is OpenAI fetching most often?
- Which document fetches later attract AI-referred visits?
- Where are Anthropic or Perplexity fetches hitting 404s?

![HitKeep AI visibility correlation card with summary KPIs and tabbed citation yield, opportunity pages, and failure hotspots tables](https://hitkeep.com/_astro/analytics-ai-visibility-correlation.C1YgNC5M_Z1AtMo9.webp)

Correlation analytics use full-width tabs so each data-dense table stays readable instead of collapsing into narrow columns.

## What the correlation report shows

The AI fetch correlation report is a **directional** report.

- The **fetch side** comes from server-side AI fetch records collected through `POST /api/sites/{id}/ingest/ai-fetch`.
- The **visit side** comes from normal human pageviews where the referrer matches a known AI assistant such as ChatGPT or Perplexity.
- Correlation happens when a fetched path later receives an AI-referred visit within the selected window.

This is intentionally not strict attribution. It is meant to answer:

> “When these AI bots fetch a page, does that page later generate AI-origin traffic?”

It does **not** claim:

> “This exact GPTBot fetch caused this exact ChatGPT referral.”

## What Google says about AI Search

Google says generative AI features in Search are rooted in the same core Search ranking and quality systems as regular Search. That makes AI Visibility a reporting workflow, not a separate “AI Search optimization” track.

Use HitKeep to find pages that deserve normal, people-first SEO work:

- Make the page’s main answer clear for human readers.
- Keep important content crawlable, visible, and easy to navigate.
- Improve titles, headings, internal links, page experience, freshness, and reliability.
- Use structured data only when it accurately matches visible page content.
- Fix 4xx, 5xx, redirect, and blocked-path issues where AI crawlers are already interested.

Google does not require `llms.txt`, content chunking, special AI schema, or AI-only rewrites for AI Overviews or AI Mode. HitKeep can show crawler interest and later AI-referred visits, but it cannot prove ranking position, citation, or referral causality.

For the baseline guidance, read Google’s [generative AI features guide](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide), [AI features and your website](https://developers.google.com/search/docs/appearance/ai-features), and [helpful, reliable, people-first content guidance](https://developers.google.com/search/docs/fundamentals/creating-helpful-content).

## Filter semantics

Assistant filters such as `assistant_name` and `assistant_family` apply to the **fetch side only**.

That means:

- filtering to `OpenAI` limits the fetched rows to OpenAI bots
- correlated visit counts still include **any** later AI-referred human visits on the same path

This is the intended product behavior. It keeps the report focused on downstream visibility rather than implying deterministic bot-to-referrer attribution.

## Metrics in the report

`GET /api/sites/{id}/ai-fetch/correlation` returns four sections:

- `summary`: total fetches, fetched paths, correlated paths, later AI-referred visits, and uncorrelated fetches
- `citation_yield`: paths with the strongest fetch-to-visit payoff
- `opportunity_pages`: heavily fetched pages with weak downstream AI traffic and/or elevated errors
- `failure_hotspots`: assistant and path-prefix combinations with concentrated 4xx/5xx issues

## Send AI fetch data into HitKeep

The browser tracker records AI-referred human visits, but it cannot reliably record AI crawler fetches. Most crawlers do not execute `hk.js`.

To populate the fetch side of this report, forward edge, proxy, CDN, or origin log records to `POST /api/sites/{id}/ingest/ai-fetch`. The provider-neutral setup guide is [AI Fetch Ingest](https://hitkeep.com/guides/tracking/ai-fetch-ingest/). The AWS guide is one implementation for CloudFront logs.

## Example request

```
curl "https://your-hitkeep.example/api/sites/{id}/ai-fetch/correlation?\
from=2026-03-01T00:00:00Z&to=2026-03-31T23:59:59Z&\
assistant_family=OpenAI&window_days=30" \
  -H "Authorization: Bearer YOUR_API_TOKEN"
```

## Example response

```
{
  "summary": {
    "total_fetches": 124,
    "fetched_paths": 38,
    "correlated_paths": 11,
    "ai_referred_visits": 27,
    "uncorrelated_fetches": 73
  },
  "citation_yield": [
    {
      "path": "/guides/ai-visibility",
      "assistant_name": "GPTBot",
      "fetch_count": 8,
      "ai_referred_visits": 5,
      "citation_yield_pct": 62.5
    }
  ],
  "opportunity_pages": [
    {
      "path": "/pricing",
      "fetch_count": 12,
      "ai_referred_visits": 1,
      "error_requests": 3,
      "error_rate_pct": 25
    }
  ],
  "failure_hotspots": [
    {
      "assistant_name": "ClaudeBot",
      "path_prefix": "/docs",
      "total_requests": 9,
      "error_requests": 4,
      "error_rate_pct": 44.44
    }
  ]
}
```

## Recommended interpretation

Use the report like this:

- **High fetches + high AI-referred visits**: pages where crawler interest and downstream AI-referred demand overlap
- **High fetches + low visits**: pages worth reviewing for helpful content, titles, structure, freshness, and reliability
- **High error hotspots**: technical issues that may reduce AI visibility even when crawlers are interested

The safest mental model is:

> fetches show AI discovery, referrals show downstream human demand, and correlation shows where those two signals overlap.

## Demo data

If you seed a local demo instance, the AI Visibility page is designed to open with realistic assistant mixes, resource-type filters, and populated correlation tabs right away instead of an empty shell.

## Related

- [How AI browsers affect web analytics](https://hitkeep.com/blog/ai-browsers-web-analytics-2026/)
- [AI Fetch Ingest](https://hitkeep.com/guides/tracking/ai-fetch-ingest/)
- [AI Fetch on AWS](https://hitkeep.com/guides/tracking/ai-fetch-aws/)
- [CloudFront AI crawler tracking](https://hitkeep.com/guides/tracking/cloudfront-ai-crawler-tracking/)
- [AI visibility reporting for SEO agencies](https://hitkeep.com/use-cases/ai-visibility-seo-agencies/)
- [AI visibility agency pilot kit](https://hitkeep.com/use-cases/ai-visibility-agency-pilot/)
- [AI visibility reporting template](https://hitkeep.com/guides/analytics/ai-seo-reporting-template/)
- [AI performance landing page](https://hitkeep.com/ai-performance/)
- [Read-only MCP Server for Web Analytics](https://hitkeep.com/use-cases/read-only-mcp-server-web-analytics/)
- [HitKeep Agent Skills](https://hitkeep.com/guides/integrations/hitkeep-agent-skills/)
- [Opportunity Recommendations](https://hitkeep.com/guides/analytics/opportunities/)
- [API Clients](https://hitkeep.com/guides/security/api-clients/)

[Previous Ask AI](https://hitkeep.com/guides/analytics/ask-ai/)[Next Chatbot analytics](https://hitkeep.com/guides/analytics/ai-chatbot-analytics/)