Recorded prompt
“How should a team track AI citations over time?”
- Product
- Perplexity
- Surface
- Perplexity Search with web search enabled
- Model
- Perplexity automatic model (model version not exposed)
- Locale
- en-US (English answer; zh-CN interface)
- Observed answer
- Open session ↗
- Observed
- 15 November 2026, 21:04 CST
- Fresh conversation
- Yes
What the answer said
11秒 Use a fixed set of prompts across the same AI engines and settings, and repeat each prompt several times so normal answer variation doesn’t skew the result. Log the exact cited URLs, then track citation rate and share of voice by engine and topic, with the formula and answer count alongside each metric. atomicagi +2 Review priority queries weekly and broader trends monthly; use a rolling baseline, investigate sustained shifts rather than reacting to a single dip, and revisit the prompt set quarterly. slatehq +2
10 recorded sources
What this observation cannot show
Authenticated free-account Perplexity browser run in a fresh conversation. The product did not expose its complete retrieval configuration. The source panel reported 10 sources and 10 unique source records were captured. Results can vary by session, locale, account state and date.