Agentic ad format | Particular Audience
An agentic ad format is an advertising unit designed for AI agents and assistants: a relevant, labelled sponsored product inside an answer, swap, reorder.
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 or basket the agent proposes to a shopper.
Examples
Sponsored products in chat, sponsored swaps, sponsored replenishment and sponsored ingredients. See Sponsored Prompts.
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 to target, while the retailer's AdOps team sets the budget, rate, dates, eligibility, approval and reporting; eligible items can then appear in chats, prompts and AI searches on the retailer's own assistants where they score highly, and the retailer's interface must show or speak the sponsored label, holding back any result that arrives without it.
Sources
- Adaptive Transformer Search MCP server (GitHub), checked 2026-10-25
How Particular Audience does it
Frequently asked questions
Does the agent decide the ad?
No. The retailer's search and rules decide; the agent presents and labels.
Related guides
- Sponsored products in agentic and conversational AI: How retailers run sponsored products inside the AI assistants they operate: relevance-first ranking, labelling, CPM and CPC pricing, pacing and holdout measurement — and why ChatGPT and Claude apps are discovery-only.
- 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.
- 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.