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 | lowes.com | 5/5 | 30 | $6 |
| 2 | homedepot.com | 4/5 | 18 | $3 |
| 3 | jeld-wen.com | 5/5 | 12 | $2 |
| 4 | menards.com | 4/5 | 8 | $1 |
| 5 | wayfair.com | 4/5 | 6 | $1 |
| 6 | thermatru.com | 4/5 | 5 | $1 |
| 7 | simpsondoor.com | 4/5 | 3 | $0 |
| 8 | build.com | 3/5 | 3 | $0 |
| 9 | solidcoredoors.com | 2/5 | 2 | $0 |
| 10 | pella.com | 4/5 | 2 | $0 |
| 11 | masonite.com | 3/5 | 1 | $0 |
| 12 | rustica.com | 3/5 | 1 | $0 |
| 13 | trustile.com | 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 →