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 | developer.mozilla.org | 5/5 | 1 | $0 |
| 2 | web.dev brand | 5/5 | 0 | $0 |
| 3 | react.dev | 5/5 | 0 | $0 |
| 4 | smashingmagazine.com | 5/5 | 0 | $0 |
| 5 | w3.org | 5/5 | 0 | $0 |
| 6 | css-tricks.com | 4/5 | 0 | $0 |
| 7 | angular.dev | 5/5 | 0 | $0 |
| 8 | vuejs.org | 5/5 | 0 | $0 |
| 9 | stackoverflow.com | 4/5 | 0 | $0 |
| 10 | nextjs.org | 5/5 | 0 | $0 |
| 11 | svelte.dev | 5/5 | 0 | $0 |
| 12 | medium.com | 4/5 | 0 | $0 |
| 13 | github.com | 5/5 | 0 | $0 |
| 14 | tailwindcss.com | 5/5 | 0 | $0 |
| 15 | bootstrap.com | 4/5 | 0 | $0 |
| 16 | remix.run | 2/5 | 0 | $0 |
| 17 | material.io | 2/5 | 0 | $0 |
| 18 | freecodecamp.org | 2/5 | 0 | $0 |
| 19 | microsoft.com | 2/5 | 0 | $0 |
| 20 | apple.com | 2/5 | 0 | $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 →