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 |
|---|---|---|---|---|
| 2 | law.cornell.edu | 5/5 | 825 | $74 |
| 6 | justia.com | 4/5 | 206 | $18 |
| 7 | supremecourt.gov | 5/5 | 151 | $13 |
| 8 | findlaw.com | 5/5 | 117 | $10 |
| 9 | cambridge.org | 2/5 | 89 | $8 |
| 10 | oxfordreference.com | 2/5 | 69 | $6 |
| 11 | oyez.org | 2/5 | 55 | $4 |
| 12 | casetext.com | 2/5 | 41 | $3 |
| 13 | uscourts.gov | 2/5 | 34 | $3 |
| 14 | legal-dictionary.thefreedictionary.com | 2/5 | 28 | $2 |
| 15 | scotusblog.com | 2/5 | 21 | $1 |
| 16 | law.com | 2/5 | 17 | $1 |
| 17 | legalmatch.com | 2/5 | 14 | $1 |
| 18 | congress.gov | 2/5 | 10 | $0 |
| 19 | amazon.com | 3/5 | 8 | $0 |
| 20 | youtube.com | 2/5 | 7 | $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 →