Methodology

Study question

Which sources do AI answer engines actually cite when asked about answer engine optimization and AI visibility?

Instrument

Each of the study's 30 category questions was asked verbatim to every enabled answer engine (chatgpt, gemini, perplexity) through their live APIs, recording the answer's cited sources. A variance panel of questions received same-day repeat draws on the primary engine to quantify test-retest stability.

The measurement path contains no LLM judgement: which domains an answer cites is read directly from the engine response; citation shares, confidence intervals (Wilson 95%), source-type classification, and flip rates are all computed in code.

Sample

• Questions: 30
• Engines: chatgpt, gemini, perplexity
• Recorded checks: 110 of 110 planned calls (0 failed — recorded as negatives)
• Test-retest repeat groups: 10
• Measured on: 2026-07-26

Every recorded check — including answers that cited no sources at all — is in the dataset.

Depth floor and refusal conditions

This study format refuses to publish below a minimum sample: at least 20 questions with recorded checks, 60 recorded checks, and 5 repeat groups. A sweep below that floor is not published as research — there is no "directional" primary data.

Limitations

• Answer engines are non-deterministic: the measured flip rate quantifies how often identical re-runs change their cited sources; single-draw results inside that noise band are not treated as findings.
• Results describe the engines' behavior at the measurement date; engine updates can shift citation patterns.
• Gemini exposes citations at lower granularity than Perplexity; per-engine counts are reported separately and never blended where instruments differ.
• The question set is the curated list published in the dataset — statistics describe this sample of questions, not every possible phrasing.

Read the full study: answer engine optimization and AI search visibility.