Skip to content
Start a free audit

Claude SEO prompt / Rankings and AI visibility

Slipped, and is an AI answer in the way

The keywords three or more places off their best, then a live AI check on up to ten of them. The table shows where an AI answer sits on a keyword that slipped; whether one caused the other is a question this data cannot settle.

Calls
rank_historyai_presence
Cadence
Monthly
Key
Content API key
All 16 prompts in the playbook

Copy the prompt

Square brackets are yours to fill before you send. In a fresh conversation, paste the brand brief from the playbook first, then this.

Call rank_history for [project name]. Take the keywords where current is worse than best by 3 or more positions. For up to ten of them, call ai_presence for [domain] in [country]. Table: keyword, best, current, AI answer shown, cited. Say which slips coincide with an AI answer we are not cited in. Report this as a coincidence in the data, not a cause.

The brief and the connect steps live on the playbook page.

What each call returns

At least one of these is a workspace tool, so the server needs a content API key from a project's Developer tab.

  • rank_history

    per market, each tracked keyword's current, best and first position with a dated series, up to 100 keywords

  • ai_presenceno key

    whether Google shows an AI Overview or AI Mode answer for a keyword, and whether the domain is cited in it

More rankings and ai visibility prompts

The tracker's own series, per market, plus a public AI check on the keywords that slipped. Nothing here reads clicks or sessions; positions are what the tool has.

Run it on your own data

A project's Developer tab issues the content API key this prompt needs. The playbook's connect steps take about two minutes.

Create a free accountConnect Claude