SEO

Measure traffic from AI assistants

Measure how many sessions ChatGPT, Perplexity, Claude, Gemini, Copilot and other AI assistants send to the site in GA4, which pages they land on, whether those visitors convert, and how the trend compares with Google organic.

The playbook

AI assistants are a small but fast-growing referral channel that most analytics setups lump into "referral" and never look at. The visitors tend to arrive with a specific question already half-answered, which makes them unusually valuable to understand. This playbook isolates them.

Steps

  1. Find the AI sources. google_analytics.run_report with dimensions: ["sessionSource", "sessionMedium"], metrics: ["sessions", "engagementRate", "conversions"] over 90 days, limit: 5000. Match sources against this list and keep them: chatgpt.com, chat.openai.com, perplexity.ai, claude.ai, gemini.google.com, copilot.microsoft.com, you.com, poe.com, meta.ai, phind.com, kagi.com. ChatGPT often appends utm_source=chatgpt.com, so the source may carry medium referral or a UTM medium; keep both.

  2. Pull the trend. google_analytics.run_report with dimensions: ["date", "sessionSource"], metrics: ["sessions"], and a dimensionFilter on sessionSource with matchType: "FULL_REGEXP" and a value like .*(chatgpt|openai|perplexity|claude\.ai|gemini\.google|copilot\.microsoft).*. Aggregate to weeks.

  3. Pull the landing pages. Same filter with dimensions: ["landingPage", "sessionSource"], metrics: ["sessions", "engagementRate", "conversions"]. These are the pages the assistants are citing.

  4. Compare with Google organic. Run the landing-page report again with dimensionFilter on sessionMedium EXACT organic. Compare total sessions, engagement rate and conversion rate. Report AI referrals as a share of organic sessions so the size is in context.

  5. Cross-reference with Search Console. google_search_console.query with dimensions: ["page"], 90 days ending 3 days ago, rowLimit: 500. Pages the assistants cite that rank weakly in Google are a distinct finding: the content works for answer engines and could work for search with the right targeting. Pages strong in both are the ones to protect.

  6. Report. Sessions by assistant with the weekly trend, the top ten AI-cited landing pages with engagement and conversions, the comparison with Google organic, and the cross-reference findings. Continue with ai-crawler-access-check if a major assistant sends nothing, since a block is the first thing to rule out.

Gotchas

  • This undercounts. Referrers are often stripped, in-app browsers may send none, and answers that are read without a click send nothing at all. The number is a floor.
  • Google AI Overviews are invisible here. Clicks from them arrive as google / organic. Search Console does not separate them either.
  • Source strings drift. chat.openai.com became chatgpt.com; new assistants appear. Check the raw source list in step 1 for anything that looks like an assistant before trusting the regex.
  • Small numbers swing. A channel with 40 sessions a week doubles and halves on noise. Report trends over weeks, not days.
  • GA4 conversions are whatever key events are configured. Say which ones you counted.

Sequel CLI

Install Sequel skills into your agent

One command connects your agent to Sequel and installs the Sequel skill, so it knows this playbook exists and reads it when a question matches. The CLI signs you in, provisions a scoped API key and writes the config for you.

Already have an MCP client?

https://api.sequel.sh/mcp

Point it at this URL and sign in when prompted, or send an API key from Settings as a Bearer token. Skills come with it; nothing else to install. Manual setup per client

  1. 1

    Install the Sequel CLI

    One line installs the latest CLI with whatever package manager you have.

    curl -fsSL https://sequel.sh/install | sh
  2. 2

    Sign in

    Authenticate in your browser and pick an organization.

    sequel login
  3. 3

    Install into your agent

    Writes the MCP config and installs the Sequel skill file for agents that support skills. Pick an agent from the list, or target one directly by its slug.

    sequel install
    • Claude Code
      sequel install claude-code
    • Claude
      sequel install claude
    • Cursor
      sequel install cursor
    • VS Code
      sequel install vscode
    • Windsurf
      sequel install windsurf
    • Zed
      sequel install zed
    • Codex
      sequel install codex
    • OpenClaw
      sequel install openclaw
    • Hermes
      sequel install hermes

More like this

Other SEO skills

Analyze high-ranking landing pages

See which pages perform best in organic search: the landing pages that earn the most clicks and impressions, the queries behind each one, and how they compare with competitor estimates from Ahrefs.

Audit internal links to important pages

Audit the site's own internal linking: crawl navigation and body links between the site's pages to find valuable pages with too few inbound internal links, orphan pages, and the handful of cross-links that would lift striking-distance rankings.

Audit or draft an llms.txt

Check whether the site has an llms.txt, whether it follows the spec and points at the pages that matter, and if it is missing draft one from the pages Search Console shows people actually find, so AI assistants get a curated map of the site instead of guessing.

Audit redirect chains and loops

Follow every redirect on the URLs Search Console still sends traffic to, on the sitemap, and on backlinked pages, to find chains, loops, redirects to the homepage, and temporary redirects that should be permanent, so link equity and crawl budget stop leaking.

Audit referring domain quality

Grade the domains linking to a site by authority, traffic and link count, spot concentration risk and link-farm patterns, and separate the referring domains that carry weight from the ones that are noise.

Audit titles and meta descriptions

Compare the title and meta description of each top page against the queries it actually ranks for in Search Console, and find missing, duplicate, truncated or misaligned metadata on the pages where a rewrite would earn the most clicks.

Put this playbook to work

Connect a source, ask the question, and the agent follows these steps. Free to start.