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.
The 5 times we asked ChatGPT this, each answer 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.
Rankings for this prompt were last re-checked in Jun 2026. We re-run higher-demand prompts more often.
| Rank | Website | Est. visits / mo |
|---|---|---|
| 1 | bandprotocol.com | 1 |
| 2 | api3.org | 1 |
| 3 | pyth.network | 1 |
| 4 | chain.link | 0 |
| 5 | supra.com | 0 |
| 6 | tellor.io | 0 |
| 7 | witnet.io | 0 |
| 8 | redstone.finance | 0 |
| 9 | chainlink.com | 0 |
| 10 | chroniclelabs.org | 0 |
| 11 | dos.network | 0 |
| 12 | nestprotocol.org | 0 |
| 13 | provable.xyz | 0 |
| 14 | switchboard.xyz | 0 |
| 15 | unmarshal.io | 0 |
| 16 | oraclize.it | 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 →