I asked ChatGPT the same question 16 times and got a different "best tool" almost every time

Hey Product Hunt,

Correction to my own post. The first version of this went live with a template placeholder still sitting in it, and it described the wrong product. Fixing it properly, because the mistake turns out to be on-topic.

MentionPop measures whether AI answer engines name your brand when someone asks for a recommendation in your category: ChatGPT, Gemini, Perplexity, Google AI Overviews. Not social listening, not alerts. The answer itself.

What pushed me to build it: I asked one engine the same buyer-intent question 16 times. Same wording, same day. It named a different "best tool" in most of the runs. If I had asked once and screenshotted the answer, I could have argued almost any conclusion I wanted, depending on which run I happened to catch.

That is the part I think most AI visibility tooling gets wrong. Ask once and you have an anecdote. What you need is a rate: named in 7 of 20 runs, plus the competitors that took the other 13.

Three things I would genuinely like this community's read on:

If you have checked whether ChatGPT or Perplexity recommends you, did you ask once or repeat it? Did the answer hold the second time?

When a competitor gets named and you do not, what do you actually do next? Content, schema, getting added to third-party listicles, something else?

Would "named in 7 of 20 runs" change your decisions differently than a plain yes or no?

And since talk is cheap: drop your domain below and I will run a free technical check and reply with what I find. Whether GPTBot, ClaudeBot and PerplexityBot are actually allowed to reach you, whether your homepage renders server-side for them or ships an empty JavaScript shell, and whether your llms.txt is valid. About a minute per site, and I will post the result either way.