A commercial recommendation prompt. We size how many people ask ChatGPT this from real search demand, then run it through ChatGPT to see which websites it recommends.
One of the 5 times we asked ChatGPT this, verbatim. The leaderboard below aggregates all 5 runs.
Aggregated across 5 runs (min 2/5 appearances). Estimated visits split the prompt's demand by rank. Sites matching the prompt's own brand are marked branded and excluded from the leaderboard.
| Rank | Website | Appears | Est. visits / mo | Est. value / mo |
|---|---|---|---|---|
| 1 | cdc.gov | 5/5 | 338 | $60 |
| 2 | who.int | 5/5 | 203 | $36 |
| 3 | epa.gov | 5/5 | 135 | $24 |
| 4 | unicef.org | 5/5 | 93 | $16 |
| 5 | water.org brand | 5/5 | 68 | $12 |
| 6 | usgs.gov | 4/5 | 51 | $9 |
| 8 | mayoclinic.org | 4/5 | 29 | $5 |
| 9 | healthline.com | 4/5 | 22 | $3 |
| 10 | nih.gov | 2/5 | 17 | $3 |
| 12 | wateraid.org | 3/5 | 10 | $1 |
| 13 | unwater.org | 3/5 | 8 | $1 |
| 14 | worldbank.org | 2/5 | 7 | $1 |
| 15 | nrdc.org | 2/5 | 5 | $0 |
ChatGPT doesn't publish prompts, so we don't show logged conversations. We measure real demand for this topic from Google search volume, scale it to ChatGPT's user base (on average about 1 ChatGPT user for every 8 Google searchers, a ratio that varies by topic), and run the prompt through ChatGPT 5 times to record which websites it recommends and in what order. Estimated visits split that demand across the recommended sites by a click-through-by-rank curve. Every number is a modeled estimate, not measured analytics. Full methodology →