An agent appears in a ChatGPT answer when ChatGPT searches the web and cites a page about that agent. OpenAI says a website is eligible only if its OAI-SearchBot crawler is allowed in robots.txt and the site's host or CDN lets OpenAI's published IP addresses through. After that, OpenAI says it ranks results "using multiple factors intended to help users find relevant, reliable information," and "placement is not guaranteed." No one can buy or promise a ChatGPT mention. Agents can make sure their pages are reachable, clear and consistent wherever ChatGPT might look.
At a glance
| Question | Short answer | Source |
|---|---|---|
| Which OpenAI crawler controls search inclusion? | OAI-SearchBot | OpenAI, Overview of OpenAI Crawlers |
| What if I block it? | Your site won't be shown in ChatGPT search answers, though it can still appear as a navigational link | OpenAI |
| Does blocking GPTBot hurt search? | Settings are independent: GPTBot governs training use, OAI-SearchBot governs search | OpenAI |
| What about ChatGPT-User? | It handles user-initiated visits, robots.txt may not apply, and it isn't used to decide search inclusion | OpenAI |
| How fast do robots.txt changes register? | About 24 hours | OpenAI |
| Can my CDN block me? | Yes. OpenAI says to confirm the host or CDN allows its published searchbot IPs | OpenAI Help |
| How does ChatGPT rank? | "Multiple factors"; "placement is not guaranteed" | OpenAI Help |
How ChatGPT finds an agent
OpenAI's help center says ChatGPT can search the web automatically when a question needs current information, or when a user asks it to. When it partners with other search providers, it typically rewrites the prompt into one or more targeted queries. It may also use approximate location from the user's IP address for local results. The answer can show inline citations and a Sources list.
A question like "who are the luxury agents in Coral Gables?" may trigger a search, and the agents named in the answer will usually be tied to the pages ChatGPT cited. OpenAI also warns that results "can be incomplete, outdated, or incorrect," so what ChatGPT says about an agent is only as good as the pages it finds.
Step 1: Make sure OpenAI can reach your site
OpenAI's crawler documentation is specific:
- OAI-SearchBot "is used to surface websites in search results in ChatGPT's search features." Sites that opt out "will not be shown in ChatGPT search answers, though can still appear as navigational links."
- OpenAI recommends allowing OAI-SearchBot in robots.txt and allowing requests from its published IP ranges (openai.com/searchbot.json).
- Changes take about 24 hours to register for search.
- GPTBot is separate. It governs whether content may be used to train OpenAI's models, and an agent can block it while still allowing search.
- ChatGPT-User fetches pages when a user asks ChatGPT to visit them. OpenAI says it isn't used to determine whether content appears in search.
The practical catch is that many brokerage and agent sites sit behind a CDN or security service with bot protection. OpenAI's help center says to "confirm that the website host or content delivery network allows traffic from OpenAI's published searchbot IP addresses." Ask your web team or brokerage IT to check, not just robots.txt.
Step 2: Give ChatGPT something clear to cite
OpenAI doesn't publish its ranking factors, so treat these as hygiene, not a formula:
- One clear page per agent. Name, brokerage, license market and areas served should be in the visible text of the page, not only in images or scripts.
- Consistency. The same name, brokerage and markets on your website, brokerage profile, Google Business Profile and directory listings make it easier for any engine to match them to one person.
- Answer real questions. Pages that plainly answer what buyers and sellers ask about your market are the kind of content a search-driven answer can cite.
- Make key facts machine-readable. Put your name, brokerage and markets in plain HTML text, and consider schema markup with
sameAslinks that tie your website, brokerage profile and other profiles to one person. OpenAI doesn't say ChatGPT uses schema, so treat this as making your pages easier for any crawler to parse, not as a ranking lever. - Don't hide pages. A page marked
noindexor blocked by robots.txt or the CDN can't do the job. - Video and transcripts help discovery elsewhere. See Video, YouTube and AI Search.
Step 3: Check what ChatGPT says, then fix the sources
Ask ChatGPT, with search on, the questions your clients would ask, and open the Sources list. It's worth asking other assistants your clients use, such as Google's AI features, the same questions, since each has its own sources. If it cites outdated or wrong pages, fix or update those pages. The same habits help with Google: see AI Overviews & Luxury Agent Discovery and How to Track AI Overviews in Search Console.
What not to believe
- "Guaranteed placement." OpenAI says placement is not guaranteed.
- "Pay to be recommended." OpenAI's ranking description doesn't include payment. Ads in ChatGPT, where offered, are a separate product with their own crawler (OAI-AdsBot).
- "Blocking GPTBot hides you from ChatGPT search." The two settings are independent.
Featured agents: Haute Real Estate Network members include Reggie Bouzy, founder and CEO of The Bouzy Group (Coldwell Banker Realty / Coldwell Banker Global Luxury), active in Jersey City and South Florida, and founder of Le Comble, an advisory focused on branded residences, and Myra Nourmand of Nourmand & Associates, who markets luxury properties from Beverly Hills to Malibu. Browse Find a Realtor.
Related
- AI Overviews & Luxury Agent Discovery
- Google Business Profile for Realtors
- Video, YouTube and AI Search
- Why Agents Are Wrong About AI Search
- AI Visibility Index
FAQ
How does ChatGPT decide which real estate agents to mention?
When ChatGPT searches the web, OpenAI says it ranks results using "multiple factors intended to help users find relevant, reliable information" and that placement isn't guaranteed. OpenAI doesn't publish the factors.
What is OAI-SearchBot?
It's OpenAI's crawler for ChatGPT search. Sites that block it won't be shown in ChatGPT search answers, though they can still appear as navigational links.
Should I block GPTBot?
That's a separate choice about AI training. OpenAI says GPTBot and OAI-SearchBot settings are independent, so blocking GPTBot doesn't by itself remove you from ChatGPT search.
My robots.txt allows OAI-SearchBot. Why might I still be missing?
OpenAI says the website host or CDN must also allow traffic from its published searchbot IP addresses. Bot-protection settings can block it even when robots.txt allows it.
How long after a fix will ChatGPT notice?
OpenAI says robots.txt changes take about 24 hours to register for search. When pages are recrawled and cited depends on OpenAI's systems.
Can I pay to be recommended by ChatGPT?
OpenAI's description of how search results are ranked doesn't include payment, and it says placement isn't guaranteed.
Does ChatGPT use my location?
OpenAI says ChatGPT may use approximate location based on IP address to return more relevant local results.
Sources
- OpenAI, Overview of OpenAI Crawlers (fetched Nov. 4, 2026)
- OpenAI Help Center, Searching the web with ChatGPT (fetched Nov. 4, 2026)
- OpenAI, searchbot.json (published IP ranges, linked from the crawler overview)