Interesting. When I’ve asked just to look at the site it seems to be okay, but asking the specific requests as you had, it came up empty on the meta-tags and schema sometimes, but always on schema. I took a look at prerender.io and they have a quick graphic that seems to explain it
Then ChatGPT mentioned this
Looks like it may or may not be an issue with Bubble versus AI crawlers. After pressing ChatGPT on the subject it responded like this
I then ran some API call tests to use GET with my blog post URL and set data type to text and have header that is user agent to test against different AI bots and google and all seem to show the correct results as if the page is accessible to the different bots. So the bots can crawl and fetch the html and robot.txts test show they are all allowed except for the version-test.
Here is final response from ChatGPT after I ran all necessary tests it provided to me for confirming whether or not my blog page could be crawled, indexed, cited by AI bots.
Got you. Short version: your page is fine. The mismatch is about me vs. real crawlers.
Why I said I couldn’t “see it”:
- In this chat I don’t crawl the web by default. Unless browsing is turned on, I can’t fetch live URLs—I can only read what you paste. So when I said I couldn’t see the structured data/metadata, that was about my session’s limitations, not your site.
What your tests prove:
robots.txt→User-agent: *with only/version-test/disallowed = all bots allowed on the live site (Googlebot, Bingbot, GPTBot, CCBot, GTBot, etc.).Fetching the article HTML with different UAs returns the page and includes JSON-LD BlogPosting + normal meta tags = machine-readable.
Schema/markup validator passes = structured data is valid.
So can ChatGPT/GPTBot “find” and cite it?
GPTBot (the crawler used for training): allowed by your robots and will be able to fetch the page. (Whether/when it’s used in model training is separate and not instant.)
ChatGPT during a conversation: it only cites pages when browsing is used in the session (or when given the direct URL). It doesn’t “know” new pages unless it browses to them or they’re already in its training/search index. That’s why I couldn’t cite it here—I wasn’t actually browsing.
Bottom line
Your site is crawlable and your post is structured and cite-ready.
My earlier “can’t see it” = chat environment limitation, not a problem with your page.
If you want extra confirmation beyond curl:
Check server logs for hits from
Googlebot,Bingbot,GPTBot, etc.Submit the URL in Search Console and Bing Webmaster Tools (fetch as bot / URL inspection).
Optional:
curl -I -A "GPTBot"against the article to confirm a 200 OK and noX-Robots-Tag: noindex.