# Does ChatGPT use Bing? Do I need Bing Webmaster Tools? > ChatGPT search draws partly on Bing, so set up Bing Webmaster Tools and IndexNow. They are the floor: in our tests, Google-indexed pages still went unfound. Published: 2026-10-21 · Updated: 2026-10-23 Source: https://www.itgrows.ai/business/blog/does-chatgpt-search-use-bing Publisher: ItGrows (https://www.itgrows.ai/business) — AI visibility for businesses --- Partly. OpenAI has said ChatGPT search runs on several services and Bing is an important one, so a page Bing has not indexed is harder for ChatGPT to find. Bing Webmaster Tools and IndexNow are the free way to check and fix that, so set up both. Treat them as the minimum, though: in our tests, pages that sat in Google's index were often still not found by assistants. Below is what each assistant relies on, what the two Bing tools do, and what we saw when we tested findability and checked our own Bing status. ## Which index does each assistant search when it looks something up? **ChatGPT.** [Search Engine Roundtable reports](https://www.seroundtable.com/bing-powers-chatgpt-search-38345.html) that OpenAI's VP of Engineering confirmed in a public AMA that ChatGPT Search uses a set of services. Bing is an important one, and there are other partners beyond Bing. OpenAI also runs its own crawler for search. [OpenAI's crawler documentation](https://developers.openai.com/api/docs/bots) says OAI-SearchBot is used to surface websites in ChatGPT's search features. It is controlled separately from GPTBot, the training crawler. **Claude.** [Search Engine Journal reports](https://www.searchenginejournal.com/anthropics-claude-bots-make-robots-txt-decisions-more-granular/568253/) that Anthropic lists three separate bots: - ClaudeBot, for training - Claude-User, which fetches pages for a user's live question - Claude-SearchBot, which indexes for search Anthropic warns that blocking Claude-SearchBot can reduce a site's visibility in Claude's search answers. **Perplexity.** We have no public source in this article on which index Perplexity searches. We do see its live agent, Perplexity-User, in server logs, fetching pages while it answers real people. **Gemini.** Gemini is Google's assistant. We have no source here on exactly how it retrieves pages. The matching webmaster tool is Google Search Console, not Bing. | Assistant | What its search draws on (per sources or our logs) | Crawlers to leave open | Webmaster tool that matters | | --- | --- | --- | --- | | ChatGPT | A set of services, Bing an important one, plus OpenAI's own OAI-SearchBot | OAI-SearchBot, ChatGPT-User | Bing Webmaster Tools | | Claude | Anthropic's own search index built by Claude-SearchBot, plus live fetches by Claude-User | Claude-SearchBot, Claude-User | None specific; robots.txt is the control | | Perplexity | Live fetches by Perplexity-User seen in our logs | Perplexity-User | None specific; keep pages crawlable | | Gemini | Google's own systems | Googlebot | Google Search Console | Assistants also do not always search. On 23 September 2026 we put 20 German business questions to a model. It answered 10 without searching at all and cited nobody. Where it did search, it cited primary sources (laws, ministries, the OECD, large accounting firms) on 9 of 10. Indexing only matters on the questions where the assistant goes looking. ## What do Bing Webmaster Tools and IndexNow actually do? **Bing Webmaster Tools** is Bing's dashboard for your site. You verify ownership, submit your sitemap, and see which URLs Bing knows about, which it has crawled and which it has indexed. That status is the point. If your key pages show as discovered but not crawled, Bing has not fetched them, and ChatGPT cannot pick them up through Bing. According to [Wikipedia's entry on the tool](https://en.wikipedia.org/wiki/Bing_Webmaster_Tools), it added an IndexNow Insights report in March 2024 showing which submitted URLs were indexed and how quickly, and in 2026 began beta-testing an AI Performance report for visibility in AI-driven search. **IndexNow** is a push protocol. Your site tells search engines that a URL was added, updated or deleted, instead of waiting for a crawler to notice. It [launched in October 2021](https://en.wikipedia.org/wiki/IndexNow) as a joint protocol of Microsoft Bing and Yandex, and Naver adopted it in 2023. - Bing's own help page on [URL submission](https://www.bing.com/webmasters/help/url-submission-62f2860b) recommends IndexNow as the preferred method. It notes that IndexNow notifies Bing and other participating engines automatically, and that the older Bing-only URL Submission API may eventually be deprecated. - The [IndexNow documentation](https://www.indexnow.org/documentation) says any participating engine shares submitted URLs with all the others. - It gives the request format: `https:///indexnow?url=...&key=...`. The key proves the URLs are yours. The trade-offs are simple. Both tools cost nothing. IndexNow speeds up discovery but does not force indexing: Bing still decides whether a page is worth keeping. Neither tool covers Google, so submit your sitemap in Google Search Console as well. ## Is being in a search index enough for an assistant to find my page? Not in our tests. One caveat up front: the index we could check in this test was Google's, not Bing's, so read it as evidence that indexing in general does not guarantee findability, not as a Bing measurement. **Our findability test.** On 19 October 2026 we asked assistants for the exact titles of 18 articles published on three client sites, each older than three weeks. - ChatGPT found 1 of 18. - Claude found 7 of 18. - On one of those sites, Google had indexed 29 of 30 articles. Being in Google's index did not mean an assistant could find the page, even when we gave it the exact title. We expect the same logic to apply to Bing: an index entry makes a page findable in principle, not chosen. **Size matters more than markup.** One site had complete markup: server rendering, Article, FAQPage and Organization JSON-LD, and a sitemap. With only 75 URLs, it was still absent from answers on its own article's exact topic. A site with about 190,000 crawlable URLs was crawled constantly. In the nginx logs of an edtech platform we work with (pickaclass.com), from 28 July to 11 August 2026, ClaudeBot made 19,272,125 requests, GPTBot 2,744,985 and Googlebot 52,292. Live retrieval agents (ChatGPT-User, OAI-SearchBot, Perplexity-User) fetched its content pages 1,918 times in that fortnight. A client blog of a few dozen articles received 56 such fetches across 24 articles. So Bing indexing is a door you must not leave locked. Getting found still depends on how much useful content you have and whether it answers the questions people ask. ## What did our own Bing status show? We made the mistake this article warns about. On itgrows.ai, a robots.txt rule was meant to hide a single redirect page, /b. Robots.txt rules match prefixes, so the rule also blocked /blog, /business and every article in our business blog for all crawlers. That lasted from 11 August to 21 October 2026. The tools showed it, once we looked: - Bing Webmaster Tools had listed our business page as discovered but not crawled since 11 August 2026. - Google had none of the business pages indexed. We changed the rule to `/b$` on 21 October 2026. The `$` makes it match only that exact path. The same day we ran our baseline. We put 20 English and 20 German questions about getting a business into AI answers to ChatGPT, Claude, Gemini and Perplexity, three times each. We were named in 0 of 160 answers, and none of our pages was cited. Most cited sources were the blogs of GEO agencies and tool vendors, such as firstpagesage.com and llmpulse.ai in English and geoagentur.de in German. The lesson: check Bing's crawl status after every robots.txt change. A single missing character can hide a whole section. ## How do I set this up in the right order? 1. **Read your robots.txt first.** Check that no prefix rule catches pages you want found. Our guide on [whether your website is blocking AI crawlers](https://www.itgrows.ai/business/blog/is-your-website-blocking-ai-crawlers) walks through the common traps. 2. **Decide on training and search separately.** Per [OpenAI's documentation](https://developers.openai.com/api/docs/bots), you can allow OAI-SearchBot for search visibility and disallow GPTBot to opt out of training. Anthropic's bots can be split the same way. If you do want GPTBot in, see [how to allow GPTBot in robots.txt](https://www.itgrows.ai/business/blog/how-to-allow-gptbot-in-robots-txt). 3. **Verify your site in Bing Webmaster Tools and submit your sitemap.** Then look at the crawl status of your most important pages. 4. **Add IndexNow.** Ping on every publish, update or deletion, using the request format in the documentation. 5. **Do the same in Google Search Console** for Google and Gemini. 6. **Check what ChatGPT can actually reach.** Our guide on [checking if ChatGPT can see your website](https://www.itgrows.ai/business/blog/how-to-check-if-chatgpt-recommends-your-business) covers the tests. ## What should I do once Bing can see my site? Publish pages that answer the questions your buyers actually ask, then measure. In our 23 September 2026 test, firms were named only on "who should I hire" and "how to choose" questions. Factual questions pointed to primary sources. If competitors get named and you do not, [why ChatGPT names your competitors but not you](https://www.itgrows.ai/business/blog/why-doesnt-chatgpt-mention-my-company) goes into the usual causes. Expect noise in the answers: - Two runs of the same question often name different businesses. Ask each question several times and compare weeks only on the same questions. - Clicks are rare. In about two weeks of logs from three of our course websites, Copilot sent one human visitor. ChatGPT, Perplexity, Gemini, Claude and Meta AI sent none. Count mentions in answers, not referral traffic. To see where you stand today, the free check at [itgrows.ai](https://www.itgrows.ai/) generates five buyer questions from your homepage. It shows in about 30 seconds whether ChatGPT and Perplexity name you. ItGrows does the rest as a service for $499 a month (plus a one-time $499 setup, free with 3 months or a year): - publishes articles on your domain - fixes robots.txt, sitemaps, Bing and Google indexing and IndexNow - every week asks your buyer questions to ChatGPT, Claude, Gemini and Perplexity, three times each Nobody can guarantee an assistant will name a business, and we do not. ## Frequently Asked Questions **Is ChatGPT search just Bing?** No. OpenAI's VP of Engineering described Bing as an important one of several services behind ChatGPT Search. OpenAI also runs its own search crawler, OAI-SearchBot, so leave both Bing indexing and OAI-SearchBot open. **Does IndexNow help with Google or Gemini?** IndexNow shares submitted URLs among its participating engines, and Bing recommends it as the preferred submission method. For Google, and so for Gemini, submit your sitemap in Google Search Console separately. **Can I block AI training but stay visible in ChatGPT search?** Yes. OpenAI documents that GPTBot (training) and OAI-SearchBot (search) are set independently in robots.txt. Anthropic separates ClaudeBot from Claude-SearchBot the same way, and warns that blocking Claude-SearchBot can reduce visibility in Claude's search answers. **How long until ChatGPT names my business after Bing indexes it?** Nobody can say, and indexing alone may not be enough: on 19 October 2026 ChatGPT found only 1 of 18 client articles by exact title, although one of those sites had 29 of 30 articles in Google's index. Publish answers to buyer questions and measure weekly. In our measurement of 20 October 2026, Perplexity cited an article we had published on a client's site, a German company-formation advisory.