Microsoft documents that Copilot and Copilot Chat send generated search queries to the Bing search service to ground their responses in web data [1]. For those Microsoft surfaces, whether Bingbot can crawl your pages and whether Bing has indexed them is therefore relevant to your visibility. For ChatGPT, the sources we reviewed do not document a relationship with Bing's index, so this article does not claim one.

What is documented

StatementSourceScope
Copilot and Copilot Chat use generated search queries sent to the Bing search service to ground responses in web data[1]Microsoft's own products
Copilot Search in Bing is an AI-powered search engine for the web, distinct from Copilot Search for Microsoft 365 content[2]Two separate products with similar names
Bing Webmaster Tools is used to troubleshoot crawling and indexing issues, submit sitemaps, and view site statistics[3]Bing's webmaster portal
IndexNow is a protocol for notifying search engines when content is created, updated, or deleted[4]Discovery of changes

The second row matters for scoping. Copilot Search for Microsoft 365 content searches a organization's own data, not the public web [2]. Bing indexing has nothing to do with that product. The public-web surfaces are the ones tied to Bing.

What is not documented

None of the sources above say that ChatGPT draws on Bing's index. As far as public documentation in our notes goes, the Bing relationship is documented for Microsoft's products only.

You will see claims elsewhere that one assistant "runs on Bing" or "runs on Google". Unless a vendor product page states it for the specific feature you are asking about, treat the claim as unverified. Retrieval setups change, and a single assistant can use more than one source depending on the product and mode.

For ChatGPT and other non-Microsoft assistants, the practical step is different: check which of their crawlers your robots.txt and firewall allow. The AI crawler robots.txt check covers that.

Why Bingbot access is still worth checking

Given the grounding documented in [1], three things are reasonable to conclude, and they are inferences rather than Microsoft statements:

  • A page Bingbot cannot fetch is a page Bing cannot index from a fresh crawl.
  • A page missing from Bing's index is, in our reading, less likely to be available to a Bing search that feeds Copilot answers.
  • Microsoft does not say that indexing guarantees a citation, and nothing in the notes describes how Bing's results are ranked or selected for answers.

So the claim is narrow. Bing crawl and index status is a precondition worth verifying, not a lever with a known effect size.

Bing Webmaster Tools: what to use it for

Bing Webmaster Tools is the documented place to troubleshoot crawling and indexing issues, submit sitemaps and view site statistics [3]. The Bing Webmaster APIs expose similar functions programmatically: accessing site data, submitting URLs and sitemaps, and viewing crawl stats [3].

A minimal setup:

  1. Add and verify your site in Bing Webmaster Tools.
  2. Submit your XML sitemap. If yours is unreliable, fix it first; see the XML sitemap guide.
  3. Review the crawl and index reports for errors on your key pages.
  4. Compare what Bing reports with what you expect to be indexed. Large gaps are worth investigating before anything else.

If you automate against the Bing Webmaster APIs, note that Microsoft says the legacy SOAP and POX APIs will be retired on August 31, 2026, and sites using them need to move to REST APIs [3].

AI Performance reporting

Microsoft's Bing Webmaster blog announced AI Performance in public preview. It is described as showing when a site is cited in AI-generated answers across Microsoft Copilot, AI-generated summaries in Bing, and select partner integrations [6]. This is a preview feature from a single announcement, so check whether it appears in your account and what it reports before building a process around it. Its scope is Microsoft's surfaces and named partners, not AI search in general.

IndexNow: telling Bing about changes

IndexNow lets you notify participating search engines when content is created, updated, or deleted, so they can crawl and reflect changes faster [4]. It is a notification mechanism. Nothing in the notes says that a submission guarantees crawling or indexing, so treat it as a prompt, not a command.

Inside Bing Webmaster Tools, IndexNow Insights reports on submitted URLs, including how many were submitted, crawled, and indexed [5]. That makes it possible to see whether your submissions are turning into indexed pages instead of assuming they are.

Where IndexNow fits best:

  • Sites that publish or change pages often, such as news, listings and product catalogs.
  • Deletions. Notifying engines about removed URLs is part of the protocol [4].
  • Pages where a stale copy would be wrong, such as pricing or availability.

Follow the setup steps in the IndexNow documentation. If your CMS or CDN has a plugin or built-in integration, use that rather than hand-rolling requests. For how long changes take to reach answers, see AI search freshness; no engine gives a guaranteed timeline.

What to check

Run these in order.

  1. robots.txt. Confirm there is no rule blocking Bingbot, either directly or through a wildcard.

``` # Blocks Bingbot — remove or narrow if unintended User-agent: bingbot Disallow: /

# Also check that a broad rule isn't catching it User-agent: * Disallow: / ```

  1. Firewall and bot rules. A WAF or CDN bot setting can return 403 or a challenge page to Bingbot even when robots.txt is open. Check your server logs for Bingbot requests and their status codes. Confirm a request is genuine before trusting its user agent; the method in verifying crawler IPs applies to any crawler that publishes verification details.
  2. Bing Webmaster Tools. Verify the site, submit the sitemap, and look for crawl and indexing errors on your most important URLs [3].
  3. Index coverage. Compare the pages you care about with what Bing reports as indexed. Unindexed key pages come first.
  4. IndexNow. If your content changes often, enable it and read the IndexNow Insights report for submitted, crawled and indexed counts [5].
  5. Page-level basics. Status codes, canonicals and redirects affect every crawler. The technical SEO checklist covers them.
  6. API usage. If any tooling calls the legacy SOAP or POX endpoints, schedule the move to REST before the retirement date [3].

What to do next

  • Verify your site in Bing Webmaster Tools and submit your sitemap if you have not.
  • Open robots.txt and your bot-management settings and confirm Bingbot gets a 200 on your key pages.
  • Turn on IndexNow if your content changes often, and watch the submitted, crawled and indexed counts.
  • Check whether AI Performance is available in your account, and treat its data as preview-stage.
  • For ChatGPT and other assistants, test the crawlers each vendor documents rather than assuming a Bing link.