--- title: "How to Get Cited by ChatGPT: What 618 Search Queries Show" url: https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt description: "We logged 618 ChatGPT search queries: Swedish prompts were mostly searched in English and official sources dominated. 12 steps to get your pages cited." lang: en --- Alice Labs (https://alicelabs.ai/en/) Services What we do (https://alicelabs.ai/#welcome)About Alice (https://alicelabs.ai/#who-we-are)Case (https://alicelabs.ai/en/case)Insights (https://alicelabs.ai/en/insights)Contact (https://alicelabs.ai/#email-form) AI Search & LLMO How-to Guide Fresh Last reviewed: 29 September 2026 · 8d ago # How to Get Cited by ChatGPT: What 618 Search Queries Show ## TL;DR Quick Answer Cited by AI > Allow OAI-SearchBot, put the question in your title, answer it first, cite official sources and match English queries. Based on 618 ChatGPT search queries. We ran 40 buyer questions through OpenAI's model with web search switched on, five times each, and logged every search query the model sent. This guide turns what we saw, plus OpenAI's and Microsoft's own documentation, into 12 steps for getting cited. Getting cited by ChatGPT means having your page shown as a linked source when ChatGPT searches the web to answer a question. OpenAI says ChatGPT search uses third-party search providers plus content supplied by partners, and its OAI-SearchBot crawler decides which sites can appear. It is a core part of GEO and LLMO. Time 2-4 weeks Difficulty Intermediate Tools robots.txt access (OAI-SearchBot rules), Bing Webmaster Tools and IndexNow, Google Search Console… ## Before you start - Basic understanding of SEO and structured data - Access to your site's CMS and robots.txt - A list of the questions your buyers ask ## What you'll have at the end Pages that ChatGPT search can crawl, find in the languages it searches in, and cite, plus a repeatable way to check whether it does. Image: Linus Ingemarsson - Author at Alice Labs (https://alicelabs.ai/images/linus-ingemarsson.png) Written by Linus Ingemarsson: https://www.linkedin.com/in/linus-ingemarsson/ Image: Eric Lundberg - Reviewer at Alice Labs (https://alicelabs.ai/images/eric-lundberg.png) Reviewed by Eric Lundberg: https://www.linkedin.com/in/eric-lundberg-3530451bb/ Published April 16, 2026 · Updated September 29, 2026 14 min read ## 12-step process 0/12 complete 1. 01 #### Step 1: Allow OAI-SearchBot in robots.txt OpenAI states that sites opted out of OAI-SearchBot will not be shown in ChatGPT search answers. Check yourdomain.com/robots.txt and make sure OAI-SearchBot is allowed. GPTBot is a separate training crawler; blocking it does not remove you from search. OpenAI says robots.txt changes take about 24 hours to take effect. 2. 02 #### Step 2: Put the question in the title and H1 In our scan, pages whose title matched the wording of the question (for example dedicated "GEO agency" or "AI for leadership teams" pages) were cited more often than broad pages. Write one page per high-value question and use that question's words in the title and H1. 3. 03 #### Step 3: Answer the question in the first paragraph Give a short, self-contained answer in the first 40-60 words, then expand. The model runs a few searches, reads candidate pages and quotes what it can lift cleanly. A clear answer near the top is easy to extract and attribute to you. 4. 04 #### Step 4: Match the language the model searches in 187 of 299 queries generated from Swedish questions were in English, often with "Sweden" added. Swedish pages should include the English terms the model uses (GEO, RAG, AI literacy), and English pages should be framed for the local market, for example "in Sweden" or "for Swedish companies". 5. 05 #### Step 5: Cite and link the official sources the model looks for The model targeted official domains with site: operators (imy.se, learn.microsoft.com, fortnox.se, digg.se, openai.com) and usually paired a vendor with an official source. Link to the regulator, standard or vendor documentation your topic depends on, with the date you checked it. 6. 06 #### Step 6: Build entity strength around your brand The model searched known brands' domains directly (site:knowit.se, site:afry.com). Use one consistent organization name, Organization and Person schema with sameAs links to your official profiles, and a clear About page, so your brand is a recognizable entity the model can search by name. 7. 07 #### Step 7: Get indexed in Bing and submit URLs with IndexNow OpenAI says ChatGPT search uses third-party search providers and names Bing among them. Verify your site in Bing Webmaster Tools, submit your sitemap and push new or updated URLs with IndexNow. Treat Bing indexing as a baseline, not a guarantee of citation. 8. 08 #### Step 8: Show dates and keep time-sensitive pages current 11% of the model's search queries in our scan contained a year. Show a visible "Last updated" date, include datePublished and dateModified in Article schema, and put the year in titles only where the content is genuinely updated for that year. 9. 09 #### Step 9: Add clean structured data Use JSON-LD for Article, FAQPage, HowTo, Organization and Person where they fit, and validate it. OpenAI does not document schema as a ranking factor for ChatGPT search, and Google says no special markup is needed for its AI features, so treat schema as clarity for machines, not a shortcut. 10. 10 #### Step 10: Earn mentions on third-party pages in your category In our scan the model rarely relied on a vendor's own page alone. Being named on credible third-party pages (industry media, directories, comparison articles) gives the model more places to find and confirm your brand. 11. 11 #### Step 11: Track ChatGPT referrals in analytics OpenAI's publisher FAQ says ChatGPT referral links include utm_source=chatgpt.com. Filter on that source in GA4 or your analytics tool to see which pages ChatGPT sends visitors to. 12. 12 #### Step 12: Run repeatable prompt audits Write the questions your buyers actually ask, run each several times with web search on, and log the sources cited and the queries the model sends. Repeat after every change. Single runs vary too much to judge on their own. ## Key Takeaways - In our scan, 187 of 299 search queries generated from Swedish questions were in English, often with "Sweden" added. A Swedish-only page misses most of those searches. - The model used site: operators against official sources: imy.se 33 times, learn.microsoft.com 29, fortnox.se 19, digg.se 17 and openai.com 12. It usually paired a vendor with an official source. - Pages with the question's wording in the title and a short answer early were cited more often than broad service pages. - The model ran about 3 searches per answer, and 11% of its queries contained a year. Visible dates matter for those queries. - OpenAI states that sites opted out of OAI-SearchBot will not be shown in ChatGPT search answers. Blocking GPTBot only opts you out of training. - The model searched well-known brands' domains directly (site:knowit.se, site:afry.com). Entity strength decides whether you are searched for by name. 01 / 10 Step ## How ChatGPT Search Finds and Cites Sources In short ChatGPT search rewrites a question into web searches, retrieves pages through third-party search providers (OpenAI names Bing) and partner content, and cites the pages it uses. Sites must allow OAI-SearchBot to be shown in its answers. OpenAI launched ChatGPT search in October 2024. In the launch post, OpenAI said the feature "leverages third-party search providers, as well as content provided directly by our partners". Bing is the provider OpenAI names in its help documentation. OpenAI does not publish a ranking formula, so anything beyond that is inference. What OpenAI does document is crawler access. It runs three separate agents, each with its own robots.txt setting: - **OAI-SearchBot.** Used to surface websites in ChatGPT's search features. OpenAI states that sites opted out of OAI-SearchBot will not be shown in ChatGPT search answers. - **GPTBot.** Crawls content that may be used to train OpenAI's foundation models. Disallowing it opts you out of training, not out of search. - **ChatGPT-User.** Used for certain user-initiated actions, such as visiting a page a user asks about. OpenAI notes that robots.txt rules may not apply to these requests. OpenAI says it can take about 24 hours for its systems to pick up a robots.txt change. Crawler policy is usually the first thing an AI search optimization consultant (https://alicelabs.ai/en/ai-search) checks before any content work begins. 02 / 10 Step ## What We Observed in 618 ChatGPT Search Queries In short In an Alice Labs scan of 200 runs in September 2026, the model sent 618 search queries. Most queries from Swedish questions were in English, it targeted official sources with site: operators, ran about 3 searches per answer, and favored pages with the question in the title and a short answer early. Most advice on ChatGPT citation is guesswork, because OpenAI does not publish how sources are chosen. So we measured what the model does before it cites anything: the search queries it sends. ### Method - **When:** 23-25 September 2026. - **Setup:** OpenAI Responses API, model `chat-latest`, web search required on every run, user country set to Sweden. - **Prompts:** 40 buyer-style questions (half Swedish, half English) across six business needs, each run 5 times, for 200 runs in total. - **What we logged:** the 618 search queries the model itself issued, the pages it fetched and the sources it cited. ### What we saw | Observation | What the data showed | | --- | --- | | Language of queries from Swedish questions | 187 of 299 were in English, often with "Sweden" added | | site: operators against official sources | imy.se 33, learn.microsoft.com 29, fortnox.se 19, digg.se 17, openai.com 12 | | Searches per answer | About 3 on average | | Queries containing a year | 11% | | Pages cited more often | Pages with the question's wording in the title and a short answer early, such as dedicated "GEO agency" and "AI for leadership teams" pages | | Source mix in answers | Usually a vendor paired with an official source | | Brand searches | The model searched known brands' domains directly, e.g. site:knowit.se and site:afry.com | ### What it means in practice 1. **Match queries in more than one language.** If the model turns a Swedish question into an English search, a page that only uses Swedish terms is invisible to that search. Use the English terms buyers and the model use, and frame English pages for the local market. 2. **Cite official sources.** The model looks for regulators and vendor documentation on its own. Pages that link to those same sources fit the answer it is building. 3. **Put the question in the title.** One page per high-value question beats one broad page that covers ten. 4. **Answer first.** A short, direct answer near the top is easy to lift and attribute. Detail can follow. 5. **Build entity strength.** The model searched well-known brands by domain. If it does not know your brand, it will not search for you by name, so you depend entirely on matching generic queries. 03 / 10 Step ## Entity Clarity: Make Your Brand Searchable by Name In short Entity clarity means making it obvious what your page defines, who wrote it and which organization publishes it. In our scan the model searched known brands' domains directly, so a strong entity gets searched for by name. Language models work with entities: people, products, concepts and organizations. When the model already knows a brand, it can search that brand's domain directly, which is what we saw with site:knowit.se and site:afry.com. A lesser-known brand has to win on generic queries instead. To establish entity clarity, do three things: 1. **Open every key page with a definition.** State what the entity is in 40-50 words, in the first paragraph. Make it self-contained and extractable. 2. **Use consistent naming.** If your product is called "Acme Analytics," don't alternate between "our platform," "the tool," and "Acme." Consistency helps the model link mentions to the same entity. 3. **Cross-link entity signals.** Your Schema.org Organization markup, your About page, your LinkedIn profiles, and your Wikidata entry (if applicable) should all describe the same entity the same way. 04 / 10 Step ## Schema.org Markup: Useful for Clarity, Not a Shortcut In short Structured data helps machines classify your content, author and dates. OpenAI does not document schema as a ChatGPT ranking factor, and Google says no special markup is needed for its AI features. Use Article, FAQPage, HowTo, Organization and Person in JSON-LD where they fit. Structured data will not get a weak page cited. What it does is remove ambiguity about what a page is, who wrote it and when it was updated. These are the types worth having: - **Article / NewsArticle.** Declares your content type, headline, author, datePublished, and dateModified. This is the baseline. - **FAQPage.** Marks up question-answer pairs. Useful because FAQ answers are short and self-contained, which is the format the model quotes. - **HowTo.** Step-by-step instructions with name and text for procedural content. - **Organization + Person.** Establishes who publishes and who writes, with sameAs links to official profiles. Use JSON-LD and validate before deploying. Malformed schema adds noise instead of clarity. Image: Linus Ingemarsson (https://alicelabs.ai/images/linus-ingemarsson.png) Image: Eric Lundberg (https://alicelabs.ai/images/eric-lundberg.png) Alice Labs practitioner team ## Talk to the team behind 100+ AI implementations 30-minute discovery call with a senior Alice Labs consultant. No slide deck, no sales pitch — just a scoping conversation. Book a Discovery Call 05 / 10 Step ## Writing Citation-Rich Content That LLMs Prefer In short Research by Aggarwal et al. (2024) found that adding citations, statistics and quotations improved visibility in generative engines by up to 40%. In our scan the model also paired vendors with official sources, so linking to those sources fits how answers are built. The GEO paper (Aggarwal et al., 2024, arXiv:2311.09735) tested nine optimization strategies across generative engines. Three produced the largest visibility gains: 1. **Cite sources inline.** Name the study, author, or organization behind every claim. A claim with a named source is easier to trust and quote than a vague one. 2. **Include specific statistics.** Numbers with named sources give the model something concrete to extract. 3. **Add quotations from credible sources.** Quoting a regulator, standard or expert adds authority the model can attribute. Our own scan points the same way. The model searched regulators and vendor documentation directly and usually paired a vendor with an official source. A page that already links to that official source makes the pairing easy. SparkToro's 2024 zero-click study found that roughly 60% of Google searches ended without a click to any external website. Being the source that gets cited, even without a click, is part of visibility now. 06 / 10 Step ## Freshness and llms.txt: One Matters, One Is Optional In short 11% of the model's search queries in our scan contained a year, so visible dates matter for time-sensitive topics. llms.txt is a proposed standard that neither OpenAI nor Google says it uses; it is cheap but optional. Freshness showed up directly in the data: 11% of the search queries the model sent contained a year. For those queries, an undated or visibly old page is a weak match. Every key page should have: - A visible "Last updated" date on the page itself. - `datePublished` and `dateModified` in Article schema. - A regular review cycle, so statistics, links and examples stay correct. Only change the date when the content actually changes. The llms.txt file, proposed by Jeremy Howard (Answer.AI) in September 2024, sits at your domain root and gives LLMs a curated overview of your site. Follow the format at llmstxt.org: H1 site name, blockquote summary, H2 sections with bulleted links. OpenAI has not said ChatGPT search uses it, and Google states that no AI text files are needed for its AI features. Alice Labs practitioner team ## Is ChatGPT citing your competitors but not you? We run a 30-prompt ChatGPT citation audit across your top keywords to show exactly where your brand is — and isn't — getting cited today. Request ChatGPT citation audit 07 / 10 Step ## How to Measure Whether ChatGPT Is Citing You In short Measure ChatGPT citation with repeated prompt audits and analytics filtered on utm_source=chatgpt.com. Bing's AI Performance report shows Copilot and partner citations, not ChatGPT. OpenAI offers no search-console-style report for ChatGPT search. Measurement today is a three-part stack: 1. **Repeated prompt audits.** Write the questions your buyers ask and run each one several times with web search on. Log the cited sources, your position and the competitors next to you. If you use the API, also log the search queries the model sends; that is where the insights in this article came from. 2. **Analytics referrals.** OpenAI's publisher FAQ says ChatGPT referral links include `utm_source=chatgpt.com`. Filter on it in GA4 under Acquisition > Traffic Acquisition. 3. **Bing AI Performance.** Bing Webmaster Tools shows how often Microsoft Copilot and partner experiences cite your pages, and the grounding queries behind those citations. It is a useful signal for AI search in general, but it is not a ChatGPT report. Set a baseline before making changes, then rerun the same prompts after each change. Single runs vary, so compare across repeated runs. 08 / 10 Step ## 12-Point Checklist for Getting Cited by ChatGPT In short The checklist combines what OpenAI documents (OAI-SearchBot access, third-party search providers, referral tracking) with what we observed in 618 search queries (language, official sources, question-shaped titles, answer-first pages, entity strength). Items 1 and 7 are about access and come from official documentation. Items 2 to 6 and 8 come from our own scan. The rest are standard practice that makes the others easier to verify. 1. **OAI-SearchBot allowed.** Without it, OpenAI says you will not be shown in ChatGPT search answers. 2. **Question in the title.** Use the words buyers and the model use, one question per page. 3. **Answer in the first paragraph.** 40-60 words that stand on their own. 4. **Bilingual matching.** Include English terms on local-language pages and local framing on English pages. 5. **Official sources linked.** The regulator, standard or vendor documentation your topic depends on. 6. **Entity strength.** Consistent brand name, Organization schema with sameAs, a real About page. 7. **Bing indexing.** Verified in Bing Webmaster Tools, sitemap submitted, updates pushed with IndexNow. 8. **Visible dates.** For the share of queries that include a year. 9. **Clean JSON-LD.** Article, FAQPage, HowTo, Organization and Person, validated. 10. **Named author and reviewer.** Role, profile link and topical expertise. 11. **Third-party mentions.** Credible pages in your category that name you. 12. **Measurement loop.** Repeated prompt audits plus utm_source=chatgpt.com in analytics. For a deeper implementation walkthrough, see our LLM citation optimization (https://alicelabs.ai/en/insights/llmo-content-strategy) guide, or engage Alice Labs directly for AI SEO consulting (https://alicelabs.ai/en/ai-seo). Swedish readers can read about our GEO and AI search service in Swedish (https://alicelabs.ai/ai-sok). Teams staffing the citation loop internally can compare software from our directory of ai content optimization tools (https://alicelabs.ai/en/insights/ai-content-optimization-tools). 09 / 10 Step ## ChatGPT Search vs Training Data: How They Differ In short ChatGPT search retrieves live pages through search providers and OAI-SearchBot and shows linked sources. Training data is collected ahead of time (GPTBot is OpenAI's training crawler) and is not cited. Search responds to changes you make now; training data does not. ChatGPT can answer from two very different substrates, and they respond to different levers. | Dimension | ChatGPT search | Training data | | --- | --- | --- | | Source | Third-party search providers (Bing named), OAI-SearchBot, partner content | Content collected before training, including by GPTBot, plus licensed content | | Freshness | Live searches at answer time | Fixed until the next model is trained | | Citations shown | Yes, linked sources | No | | Crawler control | OAI-SearchBot in robots.txt | GPTBot in robots.txt | | What you can influence | Access, titles, answers, language, sources, dates, indexing | Long-term brand presence across the open web | Spend most of your effort on search, because it responds to changes you make now. Training data still matters indirectly: a brand the model already knows is one it can search for by name, which is what we saw with well-known consultancies in our scan. Alice Labs practitioner team Book a Discovery Call 10 / 10 Step ## Publisher Partners vs Organic Citation In short OpenAI launched ChatGPT search with content partners including the Associated Press, Axel Springer, Condé Nast, Financial Times, News Corp and Reuters. OpenAI does not document how partner content is weighted against organic results, and B2B vendors can compete on organic pages. At launch in October 2024, OpenAI named partners including the Associated Press, Axel Springer, Condé Nast, Dotdash Meredith, Financial Times, GEDI, Hearst, Le Monde, News Corp, Prisa (El País), Reuters, The Atlantic, Time and Vox Media. These are licensing and content agreements, and OpenAI says ChatGPT search uses content provided directly by partners alongside third-party search. OpenAI does not publish how much weight partner content gets. What we can say from our own scan is that for B2B buyer questions, the model built answers from vendor pages and official sources such as regulators and vendor documentation, not from news archives. Actionable read: if you sell into news-adjacent categories, a partner outlet mentioning you may matter. If you sell B2B or specialist services, focus on the organic checklist above. ## About the Authors & Reviewers Written by Image: Linus Ingemarsson - CEO & Co-Founder, Alice Labs at Alice Labs (https://alicelabs.ai/images/linus-ingemarsson.png) Linus Ingemarsson (https://www.linkedin.com/in/linus-ingemarsson/) CEO & Co-Founder, Alice Labs CEO & Co-Founder at Alice Labs. Author of 7 research reports on AI adoption, governance and labor markets cited across EU, OECD and US benchmarks. - 8+ years in AI strategy & implementation - Top-5 AI Speaker, Sweden (Mindley 2025) - 100+ enterprise AI engagements View profile: https://www.linkedin.com/in/linus-ingemarsson/ Linus Ingemarsson on LinkedIn: https://www.linkedin.com/in/linus-ingemarsson/ Email Linus Ingemarsson: linus@alicelabs.ai Reviewed by September 29, 2026 Image: Eric Lundberg - Co-Founder, Alice Labs at Alice Labs (https://alicelabs.ai/images/eric-lundberg.png) Eric Lundberg (https://www.linkedin.com/in/eric-lundberg-3530451bb/) Co-Founder, Alice Labs Co-Founder at Alice Labs. Builds AI automation, agent workflows and integration systems that hold up in real business operations. - AI automation & agent systems lead - Workflow design across 100+ deployments - Specialist in RAG, integrations & APIs View profile: https://www.linkedin.com/in/eric-lundberg-3530451bb/ Eric Lundberg on LinkedIn: https://www.linkedin.com/in/eric-lundberg-3530451bb/ Email Eric Lundberg: eric@alicelabs.ai Reviewed for technical accuracy, methodology and source integrity. · All claims trace to public sources cited in-line. ## Frequently Asked Questions ### How do you get cited by ChatGPT? Allow OAI-SearchBot in robots.txt, get indexed in Bing, and write one page per buyer question with the question in the title and a short answer first. Link official sources, match the English queries the model sends, and build a consistent brand entity. ### What does ChatGPT search for when it answers a question? In our September 2026 scan the model sent 618 search queries across 200 runs, about 3 per answer. It often used site: operators against official sources such as imy.se, learn.microsoft.com and openai.com, searched known brands' domains directly, and 11% of its queries contained a year. ### Does ChatGPT search in English when asked in Swedish? Often, yes. In our scan, 187 of 299 search queries generated from Swedish questions were in English, frequently with "Sweden" added. Swedish pages should include the English terms buyers use, and English pages should mention Sweden. The scan used the API, not the ChatGPT app. ### How does ChatGPT pick sources? OpenAI says ChatGPT search uses third-party search providers, with Bing named, plus content from partners. It does not publish ranking factors. In our scan the model favored pages with the question in the title and a short early answer, and usually paired a vendor with an official source. ### Does ChatGPT crawl my site? OpenAI runs OAI-SearchBot for ChatGPT search, GPTBot for training and ChatGPT-User for certain user-initiated visits. OAI-SearchBot and GPTBot follow their own robots.txt rules; OpenAI notes robots.txt may not apply to ChatGPT-User. Changes take about 24 hours to take effect. ### Do I need to be in the Bing index to be cited by ChatGPT? OpenAI names Bing among the third-party search providers behind ChatGPT search, so Bing indexing is a sensible baseline. OpenAI does not say it is strictly required. Verify your site in Bing Webmaster Tools, submit a sitemap and use IndexNow for new URLs. ### What is the best schema.org markup for ChatGPT? Use JSON-LD for Article, FAQPage, HowTo where relevant, and Organization plus Person with sameAs links. OpenAI does not document schema as a ranking factor, so treat it as clarity for machines rather than a shortcut to citations. ### How long until ChatGPT cites a new page? There is no official timeline. OpenAI says robots.txt changes take about 24 hours to apply, and the page must be findable through search first. Rerun the same prompts after publishing and after each change to see when it starts being cited. ### Do backlinks help with ChatGPT citations? Indirectly. ChatGPT search relies on search providers, and links and mentions help pages rank and get found there. Mentions on credible third-party pages in your category also give the model more places to find and confirm your brand. ### What does the OAI-SearchBot user agent do? OAI-SearchBot is the OpenAI crawler used to surface websites in ChatGPT search. OpenAI states that sites opted out of it will not be shown in ChatGPT search answers. It is separate from GPTBot, which collects training data, so you can allow one and block the other. ### Do OpenAI publisher deals matter for organic citation? OpenAI works with content partners such as the Associated Press, Axel Springer, Financial Times, News Corp and Reuters, but does not document how partner content is weighted. For B2B buyer questions in our scan, answers were built from vendor pages and official sources. ### Can I opt out of ChatGPT crawling? Yes. Disallow OAI-SearchBot to stay out of ChatGPT search answers and GPTBot to opt out of training. OpenAI notes that robots.txt rules may not apply to ChatGPT-User, which handles user-initiated visits. Blocking OAI-SearchBot means no ChatGPT search citations. Previous in AI Search & LLMO ### What Is LLMO? Large Language Model Optimization (2026) https://alicelabs.ai/en/insights/what-is-llmo Next in AI Search & LLMO ### AI Search Engine Market Share 2026: ChatGPT, Perplexity, Google & Microsoft https://alicelabs.ai/en/insights/ai-search-engine-market-share-2026 ## Further reading - OpenAI: Introducing ChatGPT search (Oct 2024) (https://openai.com/index/introducing-chatgpt-search/)· openai.com - OpenAI crawlers documentation (OAI-SearchBot, GPTBot, ChatGPT-User) (https://developers.openai.com/api/docs/bots)· developers.openai.com - OpenAI Help: Publishers and Developers FAQ (https://help.openai.com/en/articles/12627856-publishers-and-developers-faq)· help.openai.com - Google Search Central: AI features and your website (https://developers.google.com/search/docs/appearance/ai-features)· developers.google.com - Bing Webmaster Tools: AI Performance (https://www.bing.com/webmasters/help/ai-performance-9f8e7d6c)· bing.com - GEO: Generative Engine Optimization (Aggarwal et al., 2024) (https://arxiv.org/abs/2311.09735)· arxiv.org ## Related services AI SEO consulting Alice Labs AI SEO service page: LLMO, crawler access and Bing indexability engagements.: https://alicelabs.ai/en/ai-seo AI search optimization Alice Labs AI search service: getting cited in ChatGPT, Copilot and Google AI features.: https://alicelabs.ai/en/ai-search GEO-byrå: AI-sök och synlighet i ChatGPT (svenska) Alice Labs Swedish GEO and AI search page for companies in Sweden.: https://alicelabs.ai/ai-sok ## Related reading glossary ### What Is LLMO? Large Language Model Optimization Explained Glossary definition of LLMO — the overarching discipline behind ChatGPT citation optimization. 7 min https://alicelabs.ai/en/insights/what-is-llmo comparison ### GEO vs SEO: What's the Difference? Side-by-side comparison of generative engine optimization and search engine optimization. 8 min https://alicelabs.ai/en/insights/geo-vs-seo pillar ### AI Search Optimization: Complete Guide for 2026 Full playbook covering ChatGPT, Perplexity, Claude, and Google AI Overviews. 14 min https://alicelabs.ai/en/insights/ai-search-optimization-guide ## Sources 1. Alice Labs LLM scan: 618 model-issued search queries, OpenAI Responses API, country SE (23-25 Sep 2026) (https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt)(accessed 2026-09-29) 2. OpenAI: Introducing ChatGPT search (https://openai.com/index/introducing-chatgpt-search/)(accessed 2026-09-29) 3. OpenAI crawlers documentation (OAI-SearchBot, GPTBot, ChatGPT-User) (https://developers.openai.com/api/docs/bots)(accessed 2026-09-29) 4. OpenAI Help Center: Publishers and Developers FAQ (https://help.openai.com/en/articles/12627856-publishers-and-developers-faq)(accessed 2026-09-29) 5. Google Search Central: AI features and your website (https://developers.google.com/search/docs/appearance/ai-features)(accessed 2026-09-29) 6. Bing Webmaster Tools: AI Performance (https://www.bing.com/webmasters/help/ai-performance-9f8e7d6c)(accessed 2026-09-29) 7. Aggarwal et al.: GEO: Generative Engine Optimization (arXiv:2311.09735) (https://arxiv.org/abs/2311.09735)(accessed 2026-09-29) 8. llms.txt proposal (Answer.AI) (https://llmstxt.org/)(accessed 2026-09-29) Next scheduled review: 2026-12-29 Alice Labs practitioner team Book a Discovery Call Share Share on LinkedIn (https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Falicelabs.ai%2Fen%2Finsights%2Fhow-to-get-cited-by-chatgpt)Share on X (https://twitter.com/intent/tweet?url=https%3A%2F%2Falicelabs.ai%2Fen%2Finsights%2Fhow-to-get-cited-by-chatgpt&text=How%20to%20Get%20Cited%20by%20ChatGPT%3A%20What%20618%20Search%20Queries%20Show) ## Get in Touch! The lab usually responds within 24 hours. Need help with AI? Get in touch (https://alicelabs.ai/en/ai-consulting-services#contact-form) ## Structured data ```json [ { "@context": "https://schema.org", "@graph": [ { "@type": "Organization", "@id": "https://alicelabs.ai/#organization", "name": "Alice Labs", "alternateName": [ "Alice Labs AB", "AliceLabs" ], "legalName": "Alice Labs AB", "identifier": "559443-5470", "foundingLocation": { "@type": "Place", "name": "Stockholm, Sweden" }, "url": "https://alicelabs.ai", "logo": { "@type": "ImageObject", "@id": "https://alicelabs.ai/#logo", "url": "https://alicelabs.ai/images/alice-logo.png", "contentUrl": "https://alicelabs.ai/images/alice-logo.png", "width": 2000, "height": 2027, "caption": "Alice Labs" }, "image": { "@id": "https://alicelabs.ai/#logo" }, "description": "Alice Labs är en svensk AI-byrå som hjälper företag implementera AI - från strategi till skalning.", "slogan": "From AI strategy to measurable results.", "foundingDate": "2023", "email": "hej@alicelabs.ai", "telephone": "+46734157476", "address": { "@type": "PostalAddress", "streetAddress": "Hammarbybacken 27", "addressLocality": "Stockholm", "postalCode": "120 30", "addressCountry": "SE" }, "contactPoint": [ { "@type": "ContactPoint", "contactType": "customer service", "email": "hej@alicelabs.ai", "telephone": "+46734157476", "areaServed": [ "SE", "EU" ], "availableLanguage": [ "Swedish", "English" ] } ], "areaServed": [ { "@type": "Country", "name": "Sweden" }, { "@type": "Place", "name": "Europe" } ], "knowsAbout": [ "AI strategy", "AI implementation", "AI agents", "AI automation", "Generative AI", "AI governance", "AI training", "Machine learning", "Large language models", "RAG", "AI consulting", "Digital transformation", "AI search optimization", "LLMO", "AI for enterprise" ], "founder": [ { "@id": "https://alicelabs.ai/#linus" }, { "@id": "https://alicelabs.ai/#eric" } ], "sameAs": [ "https://www.linkedin.com/company/alicelabsai", "https://www.trustpilot.com/review/alicelabs.ai", "https://www.wikidata.org/wiki/Q140369570" ] }, { "@type": "Person", "@id": "https://alicelabs.ai/#linus", "name": "Linus Ingemarsson", "givenName": "Linus", "familyName": "Ingemarsson", "jobTitle": "Co-Founder", "description": "Co-founder of Alice Labs. Architects AI agent systems and automation in production for clients across financial services, media, and the public sector.", "url": "https://alicelabs.ai/en/linus-ingemarsson", "sameAs": [ "https://www.linkedin.com/in/linus-ingemarsson/", "https://www.wikidata.org/wiki/Q140369914" ], "knowsAbout": [ "AI agents", "agent orchestration", "AI implementation", "LangGraph", "RAG systems", "AI strategy", "enterprise AI", "AI search optimization", "LLMO", "Nordic AI ecosystem" ], "worksFor": { "@id": "https://alicelabs.ai/#organization" } }, { "@type": "Person", "@id": "https://alicelabs.ai/#eric", "name": "Eric Lundberg", "givenName": "Eric", "familyName": "Lundberg", "jobTitle": "Co-Founder", "description": "Co-founder of Alice Labs. Designs AI automation systems and agent workflows that remove repetitive work and make day-to-day operations more reliable.", "url": "https://alicelabs.ai/en/eric-lundberg", "sameAs": [ "https://www.linkedin.com/in/eric-lundberg-3530451bb/", "https://www.wikidata.org/wiki/Q140369978" ], "knowsAbout": [ "AI automation", "agent workflows", "AI integrations", "process automation", "knowledge systems", "AI engineering", "enterprise AI", "Nordic AI ecosystem" ], "worksFor": { "@id": "https://alicelabs.ai/#organization" } }, { "@type": "Person", "@id": "https://alicelabs.ai/#alice", "name": "Alice Holmgren", "givenName": "Alice", "familyName": "Holmgren", "jobTitle": "CEO", "description": "CEO of Alice Labs. Leads strategy and growth across the Nordic AI consulting market.", "url": "https://alicelabs.ai/en/alice-holmgren", "knowsAbout": [ "AI strategy", "AI consulting leadership", "business development", "Nordic AI ecosystem", "enterprise AI adoption", "AI program management" ], "worksFor": { "@id": "https://alicelabs.ai/#organization" } }, { "@type": [ "LocalBusiness", "ProfessionalService" ], "@id": "https://alicelabs.ai/#localbusiness", "name": "Alice Labs", "description": "AI-konsult i Stockholm. Vi hjälper företag implementera AI - från strategi till skalning. Boka möte för en kostnadsfri AI-genomgång.", "url": "https://alicelabs.ai", "logo": { "@id": "https://alicelabs.ai/#logo" }, "image": { "@id": "https://alicelabs.ai/#logo" }, "telephone": "+46734157476", "email": "hej@alicelabs.ai", "priceRange": "$$$", "currenciesAccepted": "SEK, EUR, USD", "paymentAccepted": "Invoice", "address": { "@type": "PostalAddress", "streetAddress": "Hammarbybacken 27", "addressLocality": "Stockholm", "postalCode": "120 30", "addressRegion": "Stockholms län", "addressCountry": "SE" }, "geo": { "@type": "GeoCoordinates", "latitude": 59.3018, "longitude": 18.1003 }, "areaServed": [ { "@type": "City", "name": "Stockholm" }, { "@type": "City", "name": "Göteborg" }, { "@type": "City", "name": "Malmö" }, { "@type": "City", "name": "Uppsala" }, { "@type": "Country", "name": "Sweden" } ], "openingHoursSpecification": [ { "@type": "OpeningHoursSpecification", "dayOfWeek": [ "Monday", "Tuesday", "Wednesday", "Thursday", "Friday" ], "opens": "08:00", "closes": "18:00" } ], "hasOfferCatalog": { "@type": "OfferCatalog", "name": "AI-tjänster", "itemListElement": [ { "@type": "Offer", "itemOffered": { "@type": "Service", "name": "AI-konsult" } }, { "@type": "Offer", "itemOffered": { "@type": "Service", "name": "AI-strategi" } }, { "@type": "Offer", "itemOffered": { "@type": "Service", "name": "AI-implementation" } }, { "@type": "Offer", "itemOffered": { "@type": "Service", "name": "AI-utbildning" } }, { "@type": "Offer", "itemOffered": { "@type": "Service", "name": "AI-agenter" } }, { "@type": "Offer", "itemOffered": { "@type": "Service", "name": "AI-automation" } } ] }, "knowsAbout": [ "AI-konsult", "AI-strategi", "AI-implementation", "AI-utbildning", "AI-agenter", "AI-automation", "Generative AI", "Machine learning", "RAG", "Large language models", "AI governance" ], "parentOrganization": { "@id": "https://alicelabs.ai/#organization" }, "sameAs": [ "https://www.linkedin.com/company/alicelabsai" ] }, { "@type": "WebSite", "@id": "https://alicelabs.ai/#website", "url": "https://alicelabs.ai", "name": "Alice Labs", "alternateName": [ "Alice Labs AB" ], "description": "AI consulting, implementation and training for businesses.", "publisher": { "@id": "https://alicelabs.ai/#organization" }, "inLanguage": [ "sv-SE", "en-US" ], "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://alicelabs.ai/?q={search_term_string}" }, "query-input": "required name=search_term_string" } } ] }, { "@context": "https://schema.org", "@graph": [ { "@type": "HowTo", "@id": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#article", "headline": "How to Get Cited by ChatGPT: What 618 Search Queries Show", "description": "We logged 618 ChatGPT search queries: Swedish prompts were mostly searched in English and official sources dominated. 12 steps to get your pages cited.", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt", "datePublished": "2026-04-16", "dateModified": "2026-09-29", "expires": "2026-12-29", "author": { "@id": "https://alicelabs.ai/#linus" }, "reviewedBy": { "@id": "https://alicelabs.ai/#eric" }, "dateReviewed": "2026-09-29", "publisher": { "@type": "Organization", "name": "Alice Labs", "url": "https://alicelabs.ai", "logo": { "@type": "ImageObject", "url": "https://alicelabs.ai/images/alice-logo.png" } }, "image": { "@type": "ImageObject", "@id": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#hero-image", "url": "https://alicelabs.ai/images/og/og-home.jpg", "contentUrl": "https://alicelabs.ai/images/og/og-home.jpg", "width": 1600, "height": 900, "caption": "How to Get Cited by ChatGPT: What 618 Search Queries Show", "creator": { "@id": "https://alicelabs.ai/#organization" }, "representativeOfPage": true, "license": "https://alicelabs.ai/terms" }, "mainEntityOfPage": { "@type": "WebPage", "@id": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt" }, "inLanguage": "en", "articleSection": "ai-search", "keywords": "how to get cited by chatgpt, what does chatgpt search for, chatgpt search queries, how does chatgpt pick sources, chatgpt seo, oai-searchbot, get cited by chatgpt search", "about": [ { "@type": "Thing", "name": "How ChatGPT Search Finds and Cites Sources", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#how-chatgpt-search-works" }, { "@type": "Thing", "name": "What We Observed in 618 ChatGPT Search Queries", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#what-we-observed-618-queries" }, { "@type": "Thing", "name": "Entity Clarity: Make Your Brand Searchable by Name", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#entity-clarity" }, { "@type": "Thing", "name": "Schema.org Markup: Useful for Clarity, Not a Shortcut", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#schema-and-structured-data" }, { "@type": "Thing", "name": "Writing Citation-Rich Content That LLMs Prefer", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#citation-rich-writing" }, { "@type": "Thing", "name": "Freshness and llms.txt: One Matters, One Is Optional", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#llms-txt-and-freshness" }, { "@type": "Thing", "name": "How to Measure Whether ChatGPT Is Citing You", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#measuring-chatgpt-citations" }, { "@type": "Thing", "name": "12-Point Checklist for Getting Cited by ChatGPT", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#twelve-signals-2026" }, { "@type": "Thing", "name": "ChatGPT Search vs Training Data: How They Differ", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#search-backend-vs-training" }, { "@type": "Thing", "name": "Publisher Partners vs Organic Citation", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#publisher-deals-vs-organic" } ], "mentions": [ { "@type": "Organization", "name": "Alice Labs", "url": "https://alicelabs.ai" }, { "@type": "Organization", "name": "OpenAI", "url": "https://openai.com" }, { "@type": "Organization", "name": "Microsoft Bing", "url": "https://www.bing.com/webmasters" }, { "@type": "Product", "name": "ChatGPT", "url": "https://chatgpt.com" }, { "@type": "Thing", "name": "OAI-SearchBot", "url": "https://developers.openai.com/api/docs/bots" }, { "@type": "Thing", "name": "Generative Engine Optimization", "url": "https://arxiv.org/abs/2311.09735" }, { "@type": "Person", "name": "Linus Ingemarsson", "url": "https://www.linkedin.com/in/linus-ingemarsson/" }, { "@type": "Person", "name": "Eric Lundberg", "url": "https://www.linkedin.com/in/eric-lundberg-3530451bb/" } ], "hasPart": [ { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "How ChatGPT Search Finds and Cites Sources", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#how-chatgpt-search-works", "description": "ChatGPT search rewrites a question into web searches, retrieves pages through third-party search providers (OpenAI names Bing) and partner content, and cites the pages it uses. Sites must allow OAI-SearchBot to be shown in its answers." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "What We Observed in 618 ChatGPT Search Queries", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#what-we-observed-618-queries", "description": "In an Alice Labs scan of 200 runs in September 2026, the model sent 618 search queries. Most queries from Swedish questions were in English, it targeted official sources with site: operators, ran about 3 searches per answer, and favored pages with the question in the title and a short answer early." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "Entity Clarity: Make Your Brand Searchable by Name", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#entity-clarity", "description": "Entity clarity means making it obvious what your page defines, who wrote it and which organization publishes it. In our scan the model searched known brands' domains directly, so a strong entity gets searched for by name." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "Schema.org Markup: Useful for Clarity, Not a Shortcut", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#schema-and-structured-data", "description": "Structured data helps machines classify your content, author and dates. OpenAI does not document schema as a ChatGPT ranking factor, and Google says no special markup is needed for its AI features. Use Article, FAQPage, HowTo, Organization and Person in JSON-LD where they fit." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "Writing Citation-Rich Content That LLMs Prefer", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#citation-rich-writing", "description": "Research by Aggarwal et al. (2024) found that adding citations, statistics and quotations improved visibility in generative engines by up to 40%. In our scan the model also paired vendors with official sources, so linking to those sources fits how answers are built." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "Freshness and llms.txt: One Matters, One Is Optional", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#llms-txt-and-freshness", "description": "11% of the model's search queries in our scan contained a year, so visible dates matter for time-sensitive topics. llms.txt is a proposed standard that neither OpenAI nor Google says it uses; it is cheap but optional." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "How to Measure Whether ChatGPT Is Citing You", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#measuring-chatgpt-citations", "description": "Measure ChatGPT citation with repeated prompt audits and analytics filtered on utm_source=chatgpt.com. Bing's AI Performance report shows Copilot and partner citations, not ChatGPT." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "12-Point Checklist for Getting Cited by ChatGPT", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#twelve-signals-2026", "description": "The checklist combines what OpenAI documents (OAI-SearchBot access, third-party search providers, referral tracking) with what we observed in 618 search queries (language, official sources, question-shaped titles, answer-first pages, entity strength)." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "ChatGPT Search vs Training Data: How They Differ", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#search-backend-vs-training", "description": "ChatGPT search retrieves live pages through search providers and OAI-SearchBot and shows linked sources. Training data is collected ahead of time (GPTBot is OpenAI's training crawler) and is not cited. Search responds to changes you make now; training data does not." }, { "@type": "WebPageElement", "isAccessibleForFree": true, "name": "Publisher Partners vs Organic Citation", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#publisher-deals-vs-organic", "description": "OpenAI launched ChatGPT search with content partners including the Associated Press, Axel Springer, Condé Nast, Financial Times, News Corp and Reuters. OpenAI does not document how partner content is weighted against organic results, and B2B vendors can compete on organic pages." } ], "speakable": { "@type": "SpeakableSpecification", "cssSelector": [ "[data-speakable='true']", "[data-snippet='true']", "[data-section-answer='true']", ".quick-answer", "h1" ] } }, { "@type": "BreadcrumbList", "@id": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#breadcrumb", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://alicelabs.ai/en" }, { "@type": "ListItem", "position": 2, "name": "Insights", "item": "https://alicelabs.ai/en/insights" }, { "@type": "ListItem", "position": 3, "name": "ai-search", "item": "https://alicelabs.ai/en/insights/ai-search" }, { "@type": "ListItem", "position": 4, "name": "How to Get Cited by ChatGPT: What 618 Search Queries Show", "item": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt" } ] }, { "@type": "Person", "@id": "https://alicelabs.ai/#eric", "name": "Eric Lundberg", "jobTitle": "Co-Founder", "worksFor": { "@id": "https://alicelabs.ai/#organization" }, "knowsAbout": [ { "@type": "DefinedTerm", "name": "AI automation", "url": "https://www.wikidata.org/wiki/Q1322483" }, { "@type": "DefinedTerm", "name": "Workflow automation", "url": "https://www.wikidata.org/wiki/Q120427660" }, { "@type": "DefinedTerm", "name": "Retrieval-Augmented Generation", "url": "https://www.wikidata.org/wiki/Q117761563" }, { "@type": "DefinedTerm", "name": "Enterprise AI implementation" } ], "sameAs": [ "https://www.linkedin.com/in/eric-lundberg-3530451bb/", "https://www.wikidata.org/wiki/Q140369978" ] }, { "@type": "Person", "@id": "https://alicelabs.ai/#linus", "name": "Linus Ingemarsson", "jobTitle": "CEO & Co-Founder", "worksFor": { "@id": "https://alicelabs.ai/#organization" }, "knowsAbout": [ { "@type": "DefinedTerm", "name": "AI agent orchestration", "url": "https://www.wikidata.org/wiki/Q98678395" }, { "@type": "DefinedTerm", "name": "AI strategy" }, { "@type": "DefinedTerm", "name": "AI search optimization (LLMO)" }, { "@type": "DefinedTerm", "name": "Enterprise AI strategy" }, { "@type": "DefinedTerm", "name": "AI consulting leadership" } ], "sameAs": [ "https://www.linkedin.com/in/linus-ingemarsson/", "https://www.wikidata.org/wiki/Q140369914" ] }, { "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "How do you get cited by ChatGPT?", "acceptedAnswer": { "@type": "Answer", "text": "Allow OAI-SearchBot in robots.txt, get indexed in Bing, and write one page per buyer question with the question in the title and a short answer first. Link official sources, match the English queries the model sends, and build a consistent brand entity." } }, { "@type": "Question", "name": "What does ChatGPT search for when it answers a question?", "acceptedAnswer": { "@type": "Answer", "text": "In our September 2026 scan the model sent 618 search queries across 200 runs, about 3 per answer. It often used site: operators against official sources such as imy.se, learn.microsoft.com and openai.com, searched known brands' domains directly, and 11% of its queries contained a year." } }, { "@type": "Question", "name": "Does ChatGPT search in English when asked in Swedish?", "acceptedAnswer": { "@type": "Answer", "text": "Often, yes. In our scan, 187 of 299 search queries generated from Swedish questions were in English, frequently with \"Sweden\" added. Swedish pages should include the English terms buyers use, and English pages should mention Sweden. The scan used the API, not the ChatGPT app." } }, { "@type": "Question", "name": "How does ChatGPT pick sources?", "acceptedAnswer": { "@type": "Answer", "text": "OpenAI says ChatGPT search uses third-party search providers, with Bing named, plus content from partners. It does not publish ranking factors. In our scan the model favored pages with the question in the title and a short early answer, and usually paired a vendor with an official source." } }, { "@type": "Question", "name": "Does ChatGPT crawl my site?", "acceptedAnswer": { "@type": "Answer", "text": "OpenAI runs OAI-SearchBot for ChatGPT search, GPTBot for training and ChatGPT-User for certain user-initiated visits. OAI-SearchBot and GPTBot follow their own robots.txt rules; OpenAI notes robots.txt may not apply to ChatGPT-User. Changes take about 24 hours to take effect." } }, { "@type": "Question", "name": "Do I need to be in the Bing index to be cited by ChatGPT?", "acceptedAnswer": { "@type": "Answer", "text": "OpenAI names Bing among the third-party search providers behind ChatGPT search, so Bing indexing is a sensible baseline. OpenAI does not say it is strictly required. Verify your site in Bing Webmaster Tools, submit a sitemap and use IndexNow for new URLs." } }, { "@type": "Question", "name": "What is the best schema.org markup for ChatGPT?", "acceptedAnswer": { "@type": "Answer", "text": "Use JSON-LD for Article, FAQPage, HowTo where relevant, and Organization plus Person with sameAs links. OpenAI does not document schema as a ranking factor, so treat it as clarity for machines rather than a shortcut to citations." } }, { "@type": "Question", "name": "How long until ChatGPT cites a new page?", "acceptedAnswer": { "@type": "Answer", "text": "There is no official timeline. OpenAI says robots.txt changes take about 24 hours to apply, and the page must be findable through search first. Rerun the same prompts after publishing and after each change to see when it starts being cited." } }, { "@type": "Question", "name": "Do backlinks help with ChatGPT citations?", "acceptedAnswer": { "@type": "Answer", "text": "Indirectly. ChatGPT search relies on search providers, and links and mentions help pages rank and get found there. Mentions on credible third-party pages in your category also give the model more places to find and confirm your brand." } }, { "@type": "Question", "name": "What does the OAI-SearchBot user agent do?", "acceptedAnswer": { "@type": "Answer", "text": "OAI-SearchBot is the OpenAI crawler used to surface websites in ChatGPT search. OpenAI states that sites opted out of it will not be shown in ChatGPT search answers. It is separate from GPTBot, which collects training data, so you can allow one and block the other." } }, { "@type": "Question", "name": "Do OpenAI publisher deals matter for organic citation?", "acceptedAnswer": { "@type": "Answer", "text": "OpenAI works with content partners such as the Associated Press, Axel Springer, Financial Times, News Corp and Reuters, but does not document how partner content is weighted. For B2B buyer questions in our scan, answers were built from vendor pages and official sources." } }, { "@type": "Question", "name": "Can I opt out of ChatGPT crawling?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Disallow OAI-SearchBot to stay out of ChatGPT search answers and GPTBot to opt out of training. OpenAI notes that robots.txt rules may not apply to ChatGPT-User, which handles user-initiated visits. Blocking OAI-SearchBot means no ChatGPT search citations." } } ] }, { "@context": "https://schema.org", "@type": "HowTo", "name": "How to Get Cited by ChatGPT: What 618 Search Queries Show", "description": "We logged 618 ChatGPT search queries: Swedish prompts were mostly searched in English and official sources dominated. 12 steps to get your pages cited.", "totalTime": "14 min read", "step": [ { "@type": "HowToStep", "position": 1, "name": "Allow OAI-SearchBot in robots.txt", "text": "OpenAI states that sites opted out of OAI-SearchBot will not be shown in ChatGPT search answers. Check yourdomain.com/robots.txt and make sure OAI-SearchBot is allowed. GPTBot is a separate training crawler; blocking it does not remove you from search. OpenAI says robots.txt changes take about 24 hours to take effect." }, { "@type": "HowToStep", "position": 2, "name": "Put the question in the title and H1", "text": "In our scan, pages whose title matched the wording of the question (for example dedicated \"GEO agency\" or \"AI for leadership teams\" pages) were cited more often than broad pages. Write one page per high-value question and use that question's words in the title and H1." }, { "@type": "HowToStep", "position": 3, "name": "Answer the question in the first paragraph", "text": "Give a short, self-contained answer in the first 40-60 words, then expand. The model runs a few searches, reads candidate pages and quotes what it can lift cleanly. A clear answer near the top is easy to extract and attribute to you." }, { "@type": "HowToStep", "position": 4, "name": "Match the language the model searches in", "text": "187 of 299 queries generated from Swedish questions were in English, often with \"Sweden\" added. Swedish pages should include the English terms the model uses (GEO, RAG, AI literacy), and English pages should be framed for the local market, for example \"in Sweden\" or \"for Swedish companies\"." }, { "@type": "HowToStep", "position": 5, "name": "Cite and link the official sources the model looks for", "text": "The model targeted official domains with site: operators (imy.se, learn.microsoft.com, fortnox.se, digg.se, openai.com) and usually paired a vendor with an official source. Link to the regulator, standard or vendor documentation your topic depends on, with the date you checked it." }, { "@type": "HowToStep", "position": 6, "name": "Build entity strength around your brand", "text": "The model searched known brands' domains directly (site:knowit.se, site:afry.com). Use one consistent organization name, Organization and Person schema with sameAs links to your official profiles, and a clear About page, so your brand is a recognizable entity the model can search by name." }, { "@type": "HowToStep", "position": 7, "name": "Get indexed in Bing and submit URLs with IndexNow", "text": "OpenAI says ChatGPT search uses third-party search providers and names Bing among them. Verify your site in Bing Webmaster Tools, submit your sitemap and push new or updated URLs with IndexNow. Treat Bing indexing as a baseline, not a guarantee of citation." }, { "@type": "HowToStep", "position": 8, "name": "Show dates and keep time-sensitive pages current", "text": "11% of the model's search queries in our scan contained a year. Show a visible \"Last updated\" date, include datePublished and dateModified in Article schema, and put the year in titles only where the content is genuinely updated for that year." }, { "@type": "HowToStep", "position": 9, "name": "Add clean structured data", "text": "Use JSON-LD for Article, FAQPage, HowTo, Organization and Person where they fit, and validate it. OpenAI does not document schema as a ranking factor for ChatGPT search, and Google says no special markup is needed for its AI features, so treat schema as clarity for machines, not a shortcut." }, { "@type": "HowToStep", "position": 10, "name": "Earn mentions on third-party pages in your category", "text": "In our scan the model rarely relied on a vendor's own page alone. Being named on credible third-party pages (industry media, directories, comparison articles) gives the model more places to find and confirm your brand." }, { "@type": "HowToStep", "position": 11, "name": "Track ChatGPT referrals in analytics", "text": "OpenAI's publisher FAQ says ChatGPT referral links include utm_source=chatgpt.com. Filter on that source in GA4 or your analytics tool to see which pages ChatGPT sends visitors to." }, { "@type": "HowToStep", "position": 12, "name": "Run repeatable prompt audits", "text": "Write the questions your buyers actually ask, run each several times with web search on, and log the sources cited and the queries the model sends. Repeat after every change. Single runs vary too much to judge on their own." } ] }, { "@context": "https://schema.org", "@type": "Dataset", "name": "How to Get Cited by ChatGPT: What 618 Search Queries Show", "description": "We logged 618 ChatGPT search queries: Swedish prompts were mostly searched in English and official sources dominated. 12 steps to get your pages cited.", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt", "datePublished": "2026-04-16", "dateModified": "2026-09-29", "creator": { "@type": "Organization", "name": "Alice Labs", "url": "https://alicelabs.ai" }, "license": "https://creativecommons.org/licenses/by/4.0/", "isAccessibleForFree": true, "keywords": [ "how to get cited by chatgpt", "what does chatgpt search for", "chatgpt search queries", "how does chatgpt pick sources", "chatgpt seo", "oai-searchbot", "get cited by chatgpt search" ] }, { "@context": "https://schema.org", "@type": "ItemList", "name": "Related articles", "itemListElement": [ { "@type": "ListItem", "position": 1, "url": "https://alicelabs.ai/en/insights/what-is-llmo", "name": "What Is LLMO? Large Language Model Optimization Explained" }, { "@type": "ListItem", "position": 2, "url": "https://alicelabs.ai/en/insights/geo-vs-seo", "name": "GEO vs SEO: What's the Difference?" }, { "@type": "ListItem", "position": 3, "url": "https://alicelabs.ai/en/insights/ai-search-optimization-guide", "name": "AI Search Optimization: Complete Guide for 2026" } ] }, { "@context": "https://schema.org", "@type": "ItemList", "name": "Table of Contents", "numberOfItems": 10, "itemListOrder": "https://schema.org/ItemListOrderAscending", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "How ChatGPT Search Finds and Cites Sources", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#how-chatgpt-search-works" }, { "@type": "ListItem", "position": 2, "name": "What We Observed in 618 ChatGPT Search Queries", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#what-we-observed-618-queries" }, { "@type": "ListItem", "position": 3, "name": "Entity Clarity: Make Your Brand Searchable by Name", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#entity-clarity" }, { "@type": "ListItem", "position": 4, "name": "Schema.org Markup: Useful for Clarity, Not a Shortcut", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#schema-and-structured-data" }, { "@type": "ListItem", "position": 5, "name": "Writing Citation-Rich Content That LLMs Prefer", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#citation-rich-writing" }, { "@type": "ListItem", "position": 6, "name": "Freshness and llms.txt: One Matters, One Is Optional", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#llms-txt-and-freshness" }, { "@type": "ListItem", "position": 7, "name": "How to Measure Whether ChatGPT Is Citing You", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#measuring-chatgpt-citations" }, { "@type": "ListItem", "position": 8, "name": "12-Point Checklist for Getting Cited by ChatGPT", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#twelve-signals-2026" }, { "@type": "ListItem", "position": 9, "name": "ChatGPT Search vs Training Data: How They Differ", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#search-backend-vs-training" }, { "@type": "ListItem", "position": 10, "name": "Publisher Partners vs Organic Citation", "url": "https://alicelabs.ai/en/insights/how-to-get-cited-by-chatgpt#publisher-deals-vs-organic" } ] } ] }, { "@context": "https://schema.org", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://alicelabs.ai/en" }, { "@type": "ListItem", "position": 2, "name": "Insights", "item": "https://alicelabs.ai/en/insights" }, { "@type": "ListItem", "position": 3, "name": "AI Search & LLMO", "item": "https://alicelabs.ai/en/insights/ai-search" }, { "@type": "ListItem", "position": 4, "name": "How to Get Cited by ChatGPT: What 618 Search Queries Show" } ] } ] ```