Observation · Microsoft Copilot

How should a new website measure citations in ChatGPT and Perplexity?

Copilot recommended platform-specific citation rate, citation share, prompt coverage, citation position and AI referral outcomes, measured against a fixed recurring benchmark set.

15 November 2026, 18:33 CSTen-US (English answer; zh-CN interface)Run 2 of 3Method v0.1
Question

Recorded prompt

“How should a new website measure citations in ChatGPT and Perplexity?”
Product
Microsoft Copilot
Surface
Microsoft Copilot web chat with web search
Model
Copilot Auto (model version not exposed)
Locale
en-US (English answer; zh-CN interface)
Observed answer
Open session ↗
Observed
15 November 2026, 18:33 CST
Fresh conversation
Yes
Answer snapshot

What the answer said

Copilot advised treating AI citations as an acquisition channel while measuring ChatGPT and Perplexity separately. It proposed five metrics: citation rate, share of visible citations, prompt coverage by query category, citation position and referral sessions or conversions. It recommended running the same benchmark prompt set weekly and reporting a compact dashboard rather than random questions or single answers. It summarized the workflow as retrieval, citation and click-through, while warning that a citation does not guarantee a visit or revenue.

Linked citations

9 recorded sources

Limitations

What this observation cannot show

Authenticated Microsoft Copilot web-chat run in a fresh conversation. The answer is a proposed measurement framework; the example dashboard values are illustrative rather than observed benchmark data.