--- type: WebPage name: Get all three stories straight. id: "https://selfe.ai/ai-discovery/resonance" url: "https://selfe.ai/ai-discovery/resonance" publisher: "did:web:selfe.ai" description: "How Selfe compares demand, your account and outside evidence to find the gaps that decide whether AI recommends you for the right thing." --- # Get all three stories straight. > How Selfe compares demand, your account and outside evidence to find the gaps that decide whether AI recommends you for the right thing. What you say, what customers ask AI for and what others say about you rarely match. Those gaps decide whether an agent recommends you for the right thing. Selfe shows which gaps to answer, verify or reject. ## Three accounts. One useful gap. Your site uses your words. Customers ask in theirs. Reviews, mentions and listings add a third account that may corroborate you or contradict you. Selfe reads all three together. It shows the demand you can meet but have not answered, what others say that your own account does not, and what is simply wrong. ## What you get. **Your account.** Your site and Echo, held as your account of what is true. **Live demand.** Real prompts, in customers' own words rather than guessed keywords. **Outside evidence.** Reviews, mentions and listings that corroborate or contradict you. **The gaps.** Prioritised differences to answer, verify or reject. **Visit Keswick** The Keswick Tourism Association itself, curating its members into one agent-readable roster, the relationship every other real entry here goes live through. **Viridian Gallery** A Keswick art gallery, connecting through its own WooCommerce shop, via Visit Keswick. ## Silence is the expensive answer. Selfe keeps comparing new prompts and outside claims with your account. It surfaces the gaps that change whether you fit, rather than asking you to answer everything. Sometimes the right correction is "not self-catering". A sourced no prevents the wrong recommendation; a sourced yes earns the right one. Reviews and listings are checked the same way, so a useful claim can be adopted and a false one challenged. ## Worth reading next The latest on how agents actually work, written as it happens. **The request behind your booking button is what matters.** A booking button helps a person start a journey. An agent needs to establish the terms of a specific request, know what it may do and carry the relevant context into the next step. **Someone asks for a dog-friendly stay in October. What happens next?** A dog-friendly stay in October sounds like a simple filter until an AI agent tries to act on it. What happens next depends on details a first-pass search never asks for. **How much does an agent need to know before it can buy?** Not everything. An AI agent working through a booking request doesn't need a business's full history, it needs the small number of facts that resolve the specific thing the person asked for. A page with forty things to say and none of them the right one loses to a page with three. ## Where do the questions and outside claims come from? From real prompts and public sources an agent can read. Resonance compares them with your account, then shows where demand, your words and outside evidence disagree. It is gap analysis, not mention collection. **Can you guarantee that ChatGPT will name us?** No. Independent models decide their own answers. Selfe makes your relevant facts available, measures whether you appear and shows the gaps between the question and your current account. It improves the basis for being chosen; it does not sell placement. **How accurate is Selfe?** Selfe does not present every claim as certain. Each important fact carries its source, freshness and confidence. When sources disagree or evidence is missing, it shows the gap and follows your rule. It can use the best-supported answer, hold it back or ask you. **Do we have to rewrite all our pages for this?** No. Selfe structures what is already there and shows what is missing or contradictory. You may choose to clarify a gap, but it does not depend on rewriting the site into machine-written copy. **What if all of this looks different in a year?** The assistants and protocols will change. Your underlying record should not need rebuilding every time they do. Selfe keeps the Echo separate from any one channel and maintains the connections around it, so a new surface can read the same business instead of starting the work again. ## Act on this - [Check whether an agent can buy from you](https://selfe.ai/agentic-commerce/buyability-check) — the free readiness scan. - [Discover venues](https://selfe.ai/api/registry/discover) — `POST`, semantic browse across the registry. - [Match a bookable answer](https://selfe.ai/api/registry/match) — `POST` with dates and party size. - [Verify Selfe's identity](https://selfe.ai/.well-known/did.json) — `did:web:selfe.ai`. - [Agent card](https://selfe.ai/.well-known/agent-card.json) — how to connect over A2A or MCP.