--- title: Semantic Site Search for Publishers description: Site search for publishers that matches meaning, not keywords — semantic search over your vectorized archive, with zero-result queries rescued and logged. url: https://www.artificialpoets.com/use-cases/intent-search/ site: Artificial Poets type: page date: 2026-08-09T19:46:31+00:00 modified: 2026-08-25T19:31:45+00:00 image: https://www.artificialpoets.com/wp-content/uploads/a13s-cards/1501-social-10778d38.png --- # Search That Understands the Question "Readers search my site and leave empty-handed — can search understand what they're actually asking?" [See it on my numbers](/request-a-demo/) Horse & Rider · Ride TV · Equine Network · Equus Magazine · The Score · Equine Network Lockup ## Search that matches words, not questions The problem - **One in ten searches returns nothing** — Zero-result rates run 10 to 15% across sites, and above 20% where the engine cannot handle synonyms or typos. - **A failed search is an exit** — Readers who cannot find what they came for leave. Most never try a second query; they try a different site. - **Readers now ask in sentences** — People trained by chatbots type a question, not a keyword. A keyword index has no idea what they meant. ## How search starts understanding the question - **Meaning, not keywords** Queries are matched against what every article is about, over the same vectorised archive that drives recommendations. - **Questions answered** A reader who types a full sentence gets the pieces that answer it. No synonym list to maintain, no zero-result page. - **Fewer exits** A search that returns the right thing keeps the reader on the site. The failed search that used to be an exit becomes a session. ## Search that matches what the reader meant, not the words they typed. Search, rebuilt Keyword search fails in two ways. It returns nothing when the reader's words do not match yours, and it returns the wrong thing when they do. Both end the visit. The Artificial Poets Platform runs site search over the same vectorised archive that drives its recommendations. A query is embedded and matched against the meaning of every article, so a full-sentence question finds the pieces that answer it even when no keyword overlaps. There is no synonym list to maintain and no zero-result page to design around. Results are ranked for the reader asking, not only for the query, so the same question from two readers can surface two different pieces. A search that returns the right thing is no longer an exit. It becomes the second page of a session that would otherwise have ended. **Introducing** ## Artificial Poets Platform One engine behind every solution on this site. It learns your archive and your readers, then acts inside your CMS, your templates and your ad stack. - It learns your archive: **Every story you have published, current again** — The engine understands each piece by what it is about, not when it ran or where it was filed. A feature from 2019 competes for the next slot on merit with one from this morning. - It reads the visit: **What a reader wants, without asking** — Interest builds from what someone actually does in the session. No login, no third-party cookies, nothing leaving your domain. Useful on the second pageview, not the tenth visit. - It chooses: **The right next read, not the popular one** — Someone comparing products and someone following a running story want different things. A most-read list gives both the same five links and serves neither. - It serves: **There before the reader leaves** — The feed, the recommendations, the search answer and the signup ask all run on the same engine, in your templates and your ad stack. Any slot that arrives with them is yours to sell. - It proves: **A lift you can defend, or we say so** — Every deployment runs beside titles that did not get it, plus a serving pause. That is how a result becomes a number you can take to a board instead of a vendor claim. ## FAQ ### What share of our searches currently comes back empty? Most publishers cannot answer that, which is the first thing worth fixing: default site search rarely reports its own failures. Industry guidance puts zero-result rates around 10 to 15%, with good implementations under 5%. We would rather start by measuring yours than quote a lift number that belongs to someone else's archive. ### If a reader misspells a name or searches an acronym, does meaning-matching make it worse? It can, which is why meaning-matching alone is not the whole answer. Embeddings are strong on synonyms and paraphrase and weak on exact tokens: proper nouns, tickers, acronyms. Those cases need literal matching alongside the semantic index, and evaluating them on your own queries is part of the baseline rather than a claim we make in advance. ### If search gets this good at answering, do readers stop opening articles? No — results are links into your archive, not a generated answer. Nothing is synthesized that could misstate your journalism, and when the archive doesn't cover a query, the page says so instead of improvising. The zero-click question-and-answer session is already happening off your property — only 4% of news consumers click through from AI chatbot answers (Reuters Institute, 2026). Search that lands the reader in your reporting brings the question back onto a surface you own. ### How long after we publish is a story findable? Indexing is continuous rather than a nightly rebuild, which matters most in the hours when a story is worth searching for. If a story is not findable in the window it matters, the search box is decoration, so treat this as something to verify on your own publishing rhythm during the baseline. ### Searchers convert 2–3× — is that your lift claim? No, and be suspicious of any vendor who quotes it as one. The commonly cited multiple (4.63% vs 2.77%, Econsultancy data) is selection bias: readers who use search were already your most engaged visitors. Our measured figures come from a comparison design on live deployments, and a search deployment gets the same treatment — baseline first, frozen metrics, a comparison group. ### Only a minority of visitors touch the search box — why invest there? Two reasons. Searchers are your highest-intent visitors, worth a disproportionate share of attention. And the query log is an asset beyond the searchers themselves: internal queries are the only consented, forward-looking first-party intent signal a publisher still owns after Google Zero. Zero-result queries map what readers asked for that you never wrote — see editorial intelligence. ### Is this a search box, or a chatbot that paraphrases our journalism back at readers? A search box. It returns your articles, attributed and linked, and it does not generate prose over them. Studies of AI-generated news answers keep finding significant sourcing and accuracy problems; the point of matching on meaning here is to find your journalism, not to summarise it. ## Related - [See What Readers Want Before You Commission It](https://www.artificialpoets.com/use-cases/editorial-intelligence/) — "What should we publish next — and what does our audience want that we've never given them?" - [Horse & Rider Grew Pages Per Session 19% Without Growing Traffic](https://www.artificialpoets.com/customers/horse-and-rider/) — In the first quarter after enabling the Artificial Poets Platform, one in six Horse & Rider readers went past the first page, up from one in ten. Three comparable titles moved less than a quarter of a point. ## Unlock new revenue with our AI Artificial Poets Platform can help you with [Book a demo](/request-a-demo/) ## Questions this page answers ### What is semantic site search for publishers? It is on-site search that matches meaning instead of words: the query is embedded as a concept and matched against what every article is about, so a reader who phrases something differently from your headline still finds the piece. It runs over the same vectorized archive that drives the recommendations. ### How does semantic search work on a publisher archive? Every article in the library is embedded by subject rather than indexed by keyword, so a 2019 feature and this morning's post compete on merit for the same query. The reader's in-session interest shapes the ranking, and results are answered with your own journalism rather than sent elsewhere. ### How much does it cost to replace site search? There is no public price list; pricing follows network size and formats. Search runs on the same vectorized archive as the recommendations, so it is an additional surface on one deployment rather than a separate product with its own integration and its own bill. ### Who is it for? Publishers whose readers search and leave empty-handed. If your search returns nothing for queries your archive can answer, or ranks by date because that is all the index knows, the loss is invisible in most analytics: the reader asked a question you had already answered and did not get it. ### What are the alternatives to semantic site search? The default CMS search matches words and usually orders by date. Hosted search products index your content well but match queries rather than meaning, and are priced as their own system. Here the index is the one already running your recommendations, which is also the index measured on live deployments. ### How do I get started? Search is enabled on the same deployment as the rest of the engine: authorization, CMS access, infrastructure access, then four weeks of measurement-only baseline while the archive is indexed, then enablement on a named day. Your existing search results give you the before to judge it against.