# Semantic search Semantic search is retrieval by meaning: the engine reads intent and entities, not just matching words. This page shows what that shift means for a small product site, how to spot it in your data, and how to write for it. Updated 2026-09-14 · Source: https://porteur.ai/glossary/semantic-search ## Definition and Google’s milestones Semantic search is retrieval by meaning rather than by matching the words of the query. Engines model intent, context and entities to judge what a page is about and whether it answers the need. Google moved this way over time: Hummingbird in 2013, RankBrain in 2015, BERT in 2019 for reading queries in context, MUM in 2021, and the generative systems behind AI Overviews and AI Mode as of 2026. For you, this means a clear, topic-led page can rank across many phrasings. Repeating one keyword does nothing if the page misses the point. ## What it changes for a small site You no longer write one page per slight wording. You write one strong page per user need and cover the subtopics users expect. - Queries fan out. A good /pricing guide might earn impressions for “pricing”, “cost”, “how much is yourproduct”, and “pricing tiers”. - Entity clarity matters. Name products, features, audiences and use cases plainly, with consistent terms across pages. - Structure matters. Headings, short paragraphs and descriptive anchors help models map sections to intents. ## How to read it in Search Console Open the Performance report and filter to a key page. Scan the Queries tab for variety of phrasings and intents, not just the head term. 1. **Check query spread** Count distinct queries. If /guides/getting-started shows clicks from “setup”, “install”, “configuration”, you are covering the topic well. 2. **Group by intent** Bucket queries by jobs to be done. For /pricing, group “cost”, “discount”, “nonprofit pricing”, “enterprise plan”. 3. **Spot gaps** If you see impressions for “annual discount” with low position, add a clear section and an anchor like /pricing#annual-discount. 4. **Look at impressions without clicks** Rising impressions across many phrasings with flat clicks hints your snippet or on-page answers are weak. Fix title, meta and on-page headings. > Rule: measure semantic coverage per page by the breadth and intent mix of its queries, not by rank for one phrase. ## How to write for meaning - Start with search intent. State the job in the h1, for example “Set up YourProduct on Shopify”. - Cover the expected subtopics. Use h2s like “Requirements”, “Step-by-step”, “Common errors”, “Pricing implications”. - Name entities. Mention product names, features, industries and file types users search for. - Use plain language. Prefer “how much does YourProduct cost” wording in a sentence over jargon. - Link related pages. From /pricing, link to /guides/billing and /security if buyers ask about them. - Write answers, not variations. One good answer section beats a list of keyword-stuffed rewrites. A fixed page reads like a help doc that anticipates questions, not a thesaurus. It earns clicks from many close variants without repeating them. ## Traps and limits - Keyword stuffing. Writing “semantic search” ten times will not move you. - Thin pages per variant. “/pricing” and “/cost” as separate pages can cannibalise each other. - Ignoring snippet quality. Weak titles and meta descriptions suppress clicks even when meaning matches. - Overfitting to AI answers. Generative results change. Keep pages useful on their own and citeable. - Entity drift. Inconsistent names across pages confuse models and users. ## Questions ### Does ChatGPT use semantic search? ChatGPT is a language model that predicts text. When paired with retrieval, it can use semantic search to find passages by meaning before answering. On its own, it does not search the web; tools wrapped around it decide if and how retrieval runs. ### Is Google a semantic search? Google uses semantic methods to understand queries and pages. Milestones include Hummingbird, RankBrain, BERT, MUM, and the generative systems behind AI Overviews and AI Mode. For you, that means topic coverage and clarity beat exact-word matching. ### What is semantic search vs vector search? Semantic search is the goal, retrieving by meaning. Vector search is a common method, storing texts as embeddings and finding nearest neighbours. You can run semantic search without vectors in some setups, but vectors are the usual way for scale. ### What is semantic search in RAG? In retrieval augmented generation, a retriever finds relevant passages, often using vector search for semantic matching. The generator then writes an answer grounded in those passages. Quality depends on both the retriever and the source content. ### How do I measure semantic coverage on a page? Use Search Console. Filter by page and review the spread of queries and their intent groups over 28 days. More diverse, relevant queries with improving positions and clicks signal stronger semantic coverage. ### How should I pick keywords for semantic SEO? Start from intent and entities, not synonyms. Map one page to one job to be done, then list the subtopics users expect. Use those as headings and anchors, and let natural wording cover variations. ## Read next - [Search intent: what the results page tells you to build](https://porteur.ai/guides/search-intent): Learn the four intents, read intent from the results page, and fix pages that will never rank by changing their kind, not just the words. - [The Search Console performance report, column by column](https://porteur.ai/guides/search-console-performance-report): Every column in the Google Search Console performance report explained with the traps that trip small sites, and how to act on each. - [How to use Google Search Console in ten minutes a week](https://porteur.ai/guides/how-to-use-google-search-console): A quick weekly routine: set four filters, compare 28 days, check pages then queries, and fix three findings, without getting lost in noise. - [Entity SEO](https://porteur.ai/glossary/entity-seo): Entity SEO makes search engines recognise your product or company as a real thing, not just words. Here is what to set up and how to check it. - [Query fan-out](https://porteur.ai/glossary/query-fan-out): Query fan-out expands one question into many sub-queries. See how it picks citations, how to spot it in your data, and how to write for it. - [Generative engine optimization (GEO): how to be named by AI answers](https://porteur.ai/guides/generative-engine-optimization): How to get your site named in AI answers: sources, crawlers, lists, structure, llms.txt, comparisons, and how to measure by asking assistants. Paste your URL to see how your pages read for meaning against the searches around them and rival pages, free in about thirty seconds with Porteur. Free check: https://porteur.ai/