WEBSITE GEO ANALYZE API
Show up clearly.
Start with evidence.
Understand how supplied AI answers represent your website. Separate mentions, citations, and accuracy—and make your source content easier to understand.
WHAT GOES IN
The right input.
The right question.
Supplied answer observations, prompt sets, source links, and relevant website content.
KEEP THE SCOPE CLEARGEO means generative engine optimization here, not geolocation. Observed citations are not a guarantee of future inclusion.
WHAT COMES OUT
A report you can use.
- Mention and citation observations
- Claim-to-source review notes
- Content clarity and consistency tasks
Keep the evidence, interpretation, and next action separate. Document missing inputs instead of filling them with guessed values.
A PRACTICAL WORKFLOW
Review how an answer cites your guide
Record the prompt and answer context, inspect the cited destination, and compare the statement with the supporting passage. Use a mismatch to create a precise editorial review task.
Explore integration patternsLOOK INSIDE THE OUTPUT
Evidence, not a mystery score.
An illustrative report for this workflow. Download the JSON to inspect the complete structure.
AI answer and source excerpt
Mentions, citations, and support are different observations.
The sample answer refers to the setup guide.
The illustrative answer contains one link to the guide.
The passage does not support the answer’s full configuration claim.
{
"schema_version": "1.0",
"report_id": "sample-website-geo",
"sample": true,
"analysis_type": "website-geo",
"status": "complete",
"target": {
"label": "Sample answer observation",
"input_kind": "AI answer and source excerpt"
},
"summary": "Mentions, citations, and support are different observations.",
"findings": [
{
"id": "f01",
"outcome": "pass",
"title": "The guide is mentioned",
"evidence": "The sample answer refers to the setup guide.",
"action": "Record the exact answer context."
},
{
"id": "f02",
"outcome": "note",
"title": "A citation is visible",
"evidence": "The illustrative answer contains one link to the guide.",
"action": "Inspect the cited passage."
},
{
"id": "f03",
"outcome": "review",
"title": "The cited passage is incomplete",
"evidence": "The passage does not support the answer’s full configuration claim.",
"action": "Clarify the guide and review the answer separately."
}
],
"not_measured": [
"Live AI-answer visibility",
"Future citation likelihood",
"All answer systems"
]
}TAKE IT FURTHER
A little context goes a long way.
Separate mentions, citations, and accuracy. Build an AI-visibility review around observations you can actually inspect.
Read the full guideBefore you connect a real source
Confirm that you are authorized to use the input. Preserve its collection context and version, agree on an acceptance rule, and decide how incomplete results should be reviewed.
- Validate the report before consuming it.
- Keep secrets out of public browser code.
- Show what was—and was not—measured.
Make your next move
a clearer one.
Explore the workflows. Inspect the evidence. Build something useful.