What is a generative engine?
A generative engine is a search system that combines several language models with a search engine: it reformulates the query, retrieves pages, summarizes them and writes an answer of its own from them, with citations to the sources used. The term was formalized in 2023 by the academic paper that named GEO, and AI Overviews, Perplexity and ChatGPT with search all fit it.
Key takeaways
- A generative engine is not a model: it is a system that puts language models together with a search engine that retrieves pages at the moment of answering.
- The GEO paper describes it in three model steps: turn the query into several searches, summarize each source and write an answer with citations.
- Each engine retrieves from a different place: Google, from its index; ChatGPT and Perplexity, with their own search crawlers, which you allow or block in robots.txt.
- An LLM without search is not a generative engine: it answers from what it learned in training and cannot cite your page.
- For a store, each step is a different door: being retrieved, having your page summarized well and getting cited.
"Generative engine" is a research term, and it has nothing to do with image generators or a video game engine. It names the system behind a written answer in AI search: not the model that writes, but the set of models and search engine that decides which pages to read and what to say with them. It is one of the families of answer engine, the one that writes with other people's pages. A store should care because every piece of that system is a point where its product page gets in or stays out, and knowing the pieces tells you where to look when it does not show up.
How it works
The term was set by Pranjal Aggarwal and his co-authors in the 2023 paper that christened GEO (Generative Engine Optimization). They present it as a new kind of search engine that uses generative models to gather and summarize information, and they formalize it under a single framework: a generative engine takes the user's query, plus personal information about the user, and returns a natural-language answer.[1]arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization Inside it has two components: a set of generative models, each with a purpose (reformulating the query, summarizing), and a search engine that returns sources for each search.[1]arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization
The flow they propose, which according to the authors closely resembled Bing Chat's when they wrote it, has three model steps:[1]arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization
- Reformulate. A model breaks the query down into several simpler searches, which the search engine understands better.
- Retrieve and summarize. The search engine returns a ranked list of sources, and another model summarizes each one.
- Answer. A third model writes a single answer from those summaries, usually structured text with citations inside.
The citations are not decoration: the authors justify them by language models' tendency to make up information, and they ask of an ideal engine that every sentence be backed by citations and every citation support its sentence.[1]arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization Those two criteria come from a 2023 audit that measured them on four search engines of this kind and found fluent answers with many unsupported claims.[2]arXiv (Nelson F. Liu, Tianyi Zhang and Percy Liang, 2023). Evaluating Verifiability in Generative Search Engines The paper also describes a conversational, multi-turn version, which fits today's assistants.[1]arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization
Google describes the same architecture in its own vocabulary. Its AI features use retrieval-augmented generation (RAG), which it also calls grounding, with its ranking systems bringing pages from its index, and query fan-out, a set of related queries the model launches at once.[3]Google Search Central. Optimizing your website for generative AI features on Google Search It is the paper's step 1 under another name.
Where each engine retrieves from
The search engine in step 2 is not the same in every service, and that decides which door a store has to keep open:
| Engine | Where it retrieves from | What your page needs |
|---|---|---|
| AI Overviews and AI Mode | Google Search's index | Be indexed and eligible to be shown with a snippet[4]Google Search Central. AI features and your website |
| ChatGPT with search | The sites it surfaces with OAI-SearchBot, its search agent | Do not block OAI-SearchBot: sites that exclude it do not appear in its search answers, except as navigation links[5]OpenAI. Overview of OpenAI Crawlers |
| Perplexity | What PerplexityBot crawls, and visits a user requests | Allow PerplexityBot; Perplexity-User visits generally ignore robots.txt[6]Perplexity. Perplexity Crawlers |
| Bing's generative search | Bing's results, combined with language models | Be in Bing's results[7]Microsoft, Bing Search blog (July 24, 2024). Introducing Bing generative search |
Each one can also use different models and techniques to write. Google warns of it even inside its own house: AI Overviews and AI Mode can give different answers and links because they do not necessarily use the same models.[4]Google Search Central. AI features and your website
In a store
A fictional example: someone asks, "20-liter dry bag for kayaking that can survive being submerged." Here is how that query goes through a generative engine, and what decides at each step whether a store that sells one gets in:
| Step | What the engine does | What decides whether your product page gets in |
|---|---|---|
| Reformulate | Launches searches like "20 L dry bag IPX7," "kayak dry bag reviews" or "IPX6 vs IPX7 difference" | That your page answers one of them, even if not the literal sentence |
| Retrieve | Brings in the best-ranked sources from its index | That the page is indexed and that its crawler can read it |
| Summarize | Condenses each source | That the protection rating, the capacity and the closure are in text, not in a photo |
| Answer | Writes and cites | That your page backs the sentence that cites it better than the others do |
The first row is the one that surprises most. Your page can get in through a search nobody typed, the one the engine generated when it reformulated, and stay out of the one the shopper did type.
What people often get wrong
That the engine searches exactly what the shopper typed. The GEO paper describes a first model that turns the query into several simpler searches,[1]arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization and Google says its AI features launch related queries at once to bring in more results.[3]Google Search Central. Optimizing your website for generative AI features on Google Search Measuring only your page's position for the literal phrase leaves out the searches through which the engine really finds it.
How to check it
- Open your
robots.txtand confirm you let OAI-SearchBot and PerplexityBot through. Changes take up to about 24 hours to show in both.[5]OpenAI. Overview of OpenAI Crawlers[6]Perplexity. Perplexity Crawlers - Confirm in Search Console that your product pages are indexed and that nothing stops them from showing a snippet, which is what Google asks for to use them in AI Overviews and AI Mode.[4]Google Search Central. AI features and your website
- Look in the server logs for visits from each crawler to your product pages: if an engine does not visit them, it cannot retrieve them.
- Write down the searches your customer's question would split into: the technical feature, the comparison, the reviews. Check that some page of yours answers each one.[1]arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization
- Run the same question in each engine and note the sources cited, in new chats and on different days: each engine retrieves from a different place and writes with different models.[4]Google Search Central. AI features and your website
Related concept: LLM
An LLM (large language model) is one piece; a generative engine is the system that uses several of those pieces alongside a search engine.[1]arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization The difference shows up in the same product: ChatGPT answering without searching is a model answering with what it learned in training, with no sources; ChatGPT with search is a generative engine, which retrieves pages and cites them. Only in the second case can your page be the source, and only there does what your page says today count.
To keep going, the generative summary explains the text this system produces, and the AI search reading path orders the rest of the terms.
Synonyms
- English
- generative engine, generative search engine
- Español
- motor de búsqueda generativo, buscador generativo
Sources
- [1] arXiv (Aggarwal, Murahari, Rajpurohit, Kalyan, Narasimhan and Deshpande; KDD 2024). GEO: Generative Engine Optimization. Accessed . ↑ ↑ ↑ ↑ ↑ ↑ ↑ ↑
- [2] arXiv (Nelson F. Liu, Tianyi Zhang and Percy Liang, 2023). Evaluating Verifiability in Generative Search Engines. Accessed . ↑
- [3] Google Search Central. Optimizing your website for generative AI features on Google Search. Accessed . ↑ ↑
- [4] Google Search Central. AI features and your website. Accessed . ↑ ↑ ↑ ↑
- [5] OpenAI. Overview of OpenAI Crawlers. Accessed . ↑ ↑
- [6] Perplexity. Perplexity Crawlers. Accessed . ↑ ↑
- [7] Microsoft, Bing Search blog (July 24, 2024). Introducing Bing generative search. Accessed . ↑
Change history
- First English version.
This definition is published under CC BY 4.0. Reuse this definition freely, crediting Clione with a link to this page.
Related terms
GEO
What GEO is in SEO, where the term comes from, what Google says about it and how to check whether ChatGPT, Perplexity or AI Mode cite your store.
Generative summary
What a generative summary is, what it is made of, why its citations don't always back what it says and how to check whether it cites your store.
Search prompt
What a search prompt is, how Claude, ChatGPT or Google's AI Mode turn it into web queries, and what your product page has to answer.
Answer engine
What an answer engine is, the three ways it answers (knowledge base, snippet or generative answer) and where your store can show up.
LLM
What an LLM is, how it predicts the text it writes, why it makes up facts and what ChatGPT or Gemini do with your store's product page.
RAG
What RAG is in AI, the paper it comes from, how Google and ChatGPT use it to answer with sources, and what part of your product page ends up in the answer.
Make your catalog easy for bots to read
Clione fills every product page with what bots read best: the JSON-LD graph with its structured data, the meta description and the FAQs. You review and press Push; then we check your live store so it all stays published.