Semantic intent matching | Particular Audience
Semantic intent matching scores how well a product fits the meaning of a request, rather than whether the same words appear. It lets ads and results match.
Semantic intent matching
Semantic intent matching scores how well a product fits the meaning of a request, rather than whether the same words appear. It lets ads and results match full-sentence questions.
In search and ads
Used by Adaptive Transformer Search for results and by Sponsored Prompts to decide which sponsored products are eligible.
Run it with Particular Audience
Sponsored Prompts runs on Adaptive Transformer Search and the open-source ATS MCP server. Advertisers pick products or a collection; each item surfaces automatically, labelled, in chats, prompts and AI searches where it scores highly.
Sources
- Adaptive Transformer Search MCP server (GitHub), checked 2026-10-25
How Particular Audience does it
Frequently asked questions
Is this the same as vector search?
Vector search is one way to do it; see [vector vs keyword search](/eo/guides/questions/vector-search-vs-keyword-search).
Related guides
- Sponsored products in agentic and conversational AI: How retailers run sponsored products inside their own AI assistant, ChatGPT app or Claude connector: relevance-first ranking, labelling, CPM and CPC pricing, pacing and holdout measurement.
- Retail MCP product search with Adaptive Transformer Search: Connect Adaptive Transformer Search to ChatGPT, Claude and onsite assistants through PA's open-source MCP server, with retailer-controlled ranking and checkout.
- Sponsored prompt: A sponsored prompt is a paid, labelled product placement inside an AI answer, triggered when the shopper's request is a strong match by meaning for a.
- Agentic ad format: An agentic ad format is an advertising unit designed for AI agents and assistants: a relevant, labelled sponsored product inside an answer, swap, reorder.