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 | producewash.com | 3/5 | 25 | $1 |
| 2 | fda.gov | 3/5 | 15 | $0 |
| 3 | cdc.gov | 3/5 | 10 | $0 |
| 4 | ucanr.edu | 3/5 | 7 | $0 |
| 5 | foodsafety.gov | 2/5 | 5 | $0 |
| 6 | extension.umn.edu | 2/5 | 4 | $0 |
| 7 | washsafe.com | 2/5 | 3 | $0 |
| 8 | extension.psu.edu | 2/5 | 2 | $0 |
| 9 | extension.arizona.edu | 2/5 | 2 | $0 |
| 10 | eatright.org | 2/5 | 1 | $0 |
| 11 | washington.edu | 2/5 | 1 | $0 |
| 12 | wholefoodsmarket.com | 2/5 | 1 | $0 |
| 13 | cornell.edu | 2/5 | 1 | $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 →