Interactive tool: persona explorer
The brand AI picks depends on who is asking
AI search engines don't give everyone the same answer. The brand they cite depends on the buyer signals in the prompt. Pick a category and a brand below and see how ChatGPT's citations shift across 6 buyer personas.
- Buyer personas in the public view
- 6
- Categories
- 23
- Buyer-intent prompts per category
- 20
Built on API system-prompt variants, fully replicable, with no scraping of consumer chat apps. The full panel covers 12 personas on 5 engines; the public view shows ChatGPT and the top 5 brands per category. Read the methodology
Persona fit for Delta
AI cites Delta most when the buyer signals they are baseline (generic shopper).
Baseline citation rate
85%
Persona-fit citation rate
85%
Lift in persona fit
0pp
Citation rate by persona and engine
Gain of 20+ pts Gain of 5+ Loss of 5+ Loss of 20+| Persona | ChatGPT |
|---|---|
| Baseline (generic shopper) | 85% |
| Budget-conscious | 20% |
| Premium buyer | 0% |
| Professional | 40% |
| First-time buyer | 50% |
| Values-driven | 60% |
Each cell is the share of 20 buyer-intent prompts where the engine cited Deltawhen given that persona's system prompt. Olive cells mark a gain of 5 or more percentage points against the engine's baseline row, grey cells a loss of 5 or more. The darkest cells flag a swing of 20 points or more. Methodology and full data are in State of AI Search and on the methodology page.
This is the largest first-party AI personalization panel we know of: 12 personas, 5 engines, 25 categories and 500 brands, 20 prompts each. Full granularity (all 12 personas, all 5 engines, per-prompt verdicts and the full brand panel) is reserved for paid customers via app.mapou.ai.
Your Panel Score for your real buyer mix
The number in your monthly board deck is the baseline number. The number that matters for your actual buyer mix is different. mapou ships persona-tuned Panel Score as part of paid engagements, with custom personas, prompt sets and brand panels.