# AgentMint.net Signals Database

> The structured catalog of agent-selection signals: what makes an AI shopping agent pick one store, product, or offer over another. Every record is evidence-typed (spec-fact, reported, or hypothesis) with a confidence level.

<!-- Canonical: https://agentmint.net/signals/ · The whole database as JSON: https://agentmint.net/signals.json · Each signal has its own record at https://agentmint.net/signals/{slug}.md · Evidence types are load-bearing: spec-fact | reported | hypothesis (no measured). -->

32 signals, grouped by funnel stage (discovery, matching, comparison, choice), then impact.

Evidence: spec-fact (official doc) | reported (named third party) | hypothesis (our inference). Confidence: very-high | high | medium | low. Impact is a 1-3 editorial priority.

## Discovery

| Signal | Definition | Evidence | Confidence | Impact | Last verified |
| --- | --- | --- | --- | --- | --- |
| [Agent infrastructure reachability](https://agentmint.net/signals/agent-infra-reachability/) | Whether a crawler you allow in robots.txt actually receives your full page - a 200 over HTTPS, not a WAF challenge, rate-limit, or geoblock - rather than being silently turned away. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Content equivalence (no cloaking)](https://agentmint.net/signals/content-equivalence-no-cloaking/) | Serving equivalent facts in different formats at one URL is legitimate content negotiation, but serving materially different content by user-agent is cloaking, a spam violation that reduces ranking eligibility. | spec-fact | Very high | 3/3 | 2026-07-08 |
| [Crawl directives (robots.txt + sitemap)](https://agentmint.net/signals/crawl-directives/) | Whether your robots.txt and XML sitemap let AI search and citation crawlers find and reach your product URLs at all. | spec-fact | Very high | 3/3 | 2026-07-08 |
| [Agent-readiness monitoring and ownership](https://agentmint.net/signals/agent-monitoring/) | Whether you actually watch that agents reach, read, and buy, by confirming agent user-agents in logs, segmenting AI-referred traffic, and giving readiness a named owner who re-checks it. | hypothesis | Low | 2/3 | 2026-07-08 |
| [llms.txt priority ordering](https://agentmint.net/signals/llms-txt-priority-order/) | The llms.txt spec exposes only two prioritization levers: the order of the link lists and reserving the 'Optional' H2 for URLs an agent may skip. | spec-fact | Very high | 2/3 | 2026-07-08 |
| [Machine-readable page representation](https://agentmint.net/signals/machine-readable-mirror/) | Serving a token-light Markdown copy of a page, either via same-URL Accept negotiation or a distinct .md mirror, and advertising it with rel=alternate, hands agents a cheaper-to-read representation of the same facts. | hypothesis | Low | 2/3 | 2026-07-08 |
| [Origin serve-ability for agents](https://agentmint.net/signals/origin-serveability/) | Keeping your origin open and cheap to serve, by edge-caching the near-static machine surfaces and allowlisting verified bots while rate-limiting only unverified spoofers, so a verified agent always gets a fast 200 instead of a block. | hypothesis | Low | 2/3 | 2026-07-08 |
| [Track AI-answer presence, not just referrals](https://agentmint.net/signals/answer-presence-tracking/) | Beyond referral traffic, you track whether each engine names or links your store for your top category queries, since answer-presence is the leading indicator of whether you're even in the consideration set. | hypothesis | Low | 2/3 | 2026-07-08 |

## Matching

| Signal | Definition | Evidence | Confidence | Impact | Last verified |
| --- | --- | --- | --- | --- | --- |
| [Offer markup completeness and truthfulness](https://agentmint.net/signals/offer-markup-completeness/) | Whether the Product/Offer JSON-LD carries a valid price and currency, truthful availability and condition, a resolvable image, and present return/shipping objects that match what the shopper and checkout see. | spec-fact | Very high | 3/3 | 2026-07-08 |
| [Server-rendered, crawlable content](https://agentmint.net/signals/crawlable-content/) | Commerce-critical fields and full policy text appear in the raw server HTML, not behind JavaScript, a PDF, or a click-to-fetch accordion, so a non-executing crawler can read them. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Product identity and canonical URL](https://agentmint.net/signals/product-identity/) | Whether each product has one stable canonical URL matching the feed link plus real manufacturer identifiers, so an agent can match your item to the same product across competing stores. | spec-fact | Very high | 2/3 | 2026-07-08 |
| [Validation hygiene (use existing validators)](https://agentmint.net/signals/validation-hygiene/) | Whether structured data, feeds, and protocol manifests are run through existing maintained validators rather than a homegrown checker. | spec-fact | Very high | 2/3 | 2026-07-08 |
| [Variants and titles use the words shoppers type](https://agentmint.net/signals/variant-and-title-matching/) | Variant names and product titles lead with explicit, literal attributes (category, size, color, material, use-case) an agent can map to a user's query, not internal codes or brand-only names. | hypothesis | Low | 2/3 | 2026-07-08 |

## Comparison

| Signal | Definition | Evidence | Confidence | Impact | Last verified |
| --- | --- | --- | --- | --- | --- |
| [Competitive price awareness with parity](https://agentmint.net/signals/price-competitive-awareness/) | Price is a real selection lever whose weight varies by model (ACES measures per-model price elasticity), so you track where your total landed cost ranks for target queries and hold price parity between agents and humans. | reported | High | 3/3 | 2026-07-08 |
| [Delivery ETA is computable per destination](https://agentmint.net/signals/delivery-eta-legibility/) | Concrete handling time, transit time, order cutoff and per-destination shipping data let an agent answer 'when will it arrive?' and 'can it arrive by [date]?' rather than defer to a competitor that can. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Descriptions answer relayed buyer questions](https://agentmint.net/signals/buyer-question-descriptions/) | Product copy answers, in buyer language, the concrete questions agents relay from users (fit, compatibility, use-case) rather than marketing fluff that dodges them. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Facts per token, complete against peers](https://agentmint.net/signals/facts-per-token/) | Your listing packs specific, verifiable facts per token (specs, price, GTIN, availability, policy) and fills the comparable attributes the top listings in your category expose, so an agent has real substance to decide on rather than superlatives. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Offer cost legibility](https://agentmint.net/signals/offer-cost-legibility/) | An agent can read your full cost on a cold product page - the current price and any sale in parseable text with currency and tax, plus shipping, fees, unit price, and any free-shipping threshold - and every figure matches checkout. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Query-conditional rewrites are a targeted experiment](https://agentmint.net/signals/description-rewrite-experiment/) | Rewriting descriptions to match likely queries produces concentrated, not universal, gains, so treat it as a measured experiment on candidate SKUs rather than a blanket promise. | reported | High | 2/3 | 2026-07-08 |
| [Return terms are fully legible](https://agentmint.net/signals/returns-legibility/) | The return window, who pays return cost, the return method, and the refund type are each stated in plain prose that matches the structured-data fields, leaving nothing for the agent to infer. | hypothesis | Low | 2/3 | 2026-07-08 |

## Choice

| Signal | Definition | Evidence | Confidence | Impact | Last verified |
| --- | --- | --- | --- | --- | --- |
| [ACP feed and checkout readiness](https://agentmint.net/signals/acp-readiness/) | Whether a store targeting ChatGPT checkout ships the ACP feed with correct eligibility flags and the return fields checkout-eligible items require. | spec-fact | Very high | 3/3 | 2026-07-08 |
| [Agent-payment rail readiness](https://agentmint.net/signals/payment-rail-readiness/) | Whether your payment stack can complete an agent-initiated purchase over rails like AP2, Visa Trusted Agent Protocol, or Mastercard Agent Pay. | reported | High | 3/3 | 2026-07-08 |
| [Audit grid position bias per provider](https://agentmint.net/signals/position-bias-audit/) | Grid position is a reported, provider-specific selection lever, so you record your rendered on-screen position per engine to avoid mistaking a position swing for a content win or loss. | reported | High | 3/3 | 2026-07-08 |
| [Defined agent win-rate measurement](https://agentmint.net/signals/agent-win-rate-measurement/) | You define agent win rate for your catalog and measure it with a fixed prompt set across ChatGPT, Gemini and Perplexity, reporting a range with stated sampling rather than a single confident number. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Earn endorsement, never self-label sponsored](https://agentmint.net/signals/endorsement-not-sponsored/) | Agents reportedly penalize a self-applied 'Sponsored' tag and reward legitimate platform endorsements, so the durable play is earning genuine editor's-pick or verified-seller status, not faking badge markup. | reported | High | 3/3 | 2026-07-08 |
| [Offer consistency and freshness across surfaces](https://agentmint.net/signals/offer-consistency-freshness/) | Price, availability, shipping, and return values show identical, current numbers across the product page, structured data, feed, and checkout, so an agent never arbitrates a conflict or quotes an offer you no longer honor. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Re-test after every major model update](https://agentmint.net/signals/retest-on-model-updates/) | Model updates can drastically reshuffle market shares, so a win measured last quarter can silently evaporate and the win-rate protocol should re-run within a set window on each major release. | reported | High | 3/3 | 2026-07-08 |
| [Review depth: count, recency, distribution](https://agentmint.net/signals/review-depth/) | Rating is a reported selection lever, so complete review data (a truthful count, recent reviews, and a full star distribution shown on the PDP) gives a rating-sensitive agent more credible depth to weigh than a bare average. | hypothesis | Low | 3/3 | 2026-07-08 |
| [Guest checkout completability](https://agentmint.net/signals/guest-checkout/) | Whether an agent with no account credentials can complete a purchase, because no forced signup, password, or email verification blocks the path. | hypothesis | Low | 2/3 | 2026-07-08 |
| [Price sensitivity varies by model](https://agentmint.net/signals/model-specific-price-sensitivity/) | The same discount moves engines differently, so a markdown that shifts share on one engine may barely move another and price strategy should be tested per engine, not blended. | reported | High | 2/3 | 2026-07-08 |
| [Seller identity reachable in two hops](https://agentmint.net/signals/seller-identity-reachable/) | A crawlable path to seller identity, address and contact within two hops of a product page signals a real, accountable merchant that trust-weighting agents won't discount. | hypothesis | Low | 2/3 | 2026-07-08 |
| [UCP profile and order-management readiness](https://agentmint.net/signals/ucp-readiness/) | Whether a store targeting Google/UCP surfaces publishes a public /.well-known/ucp profile and can return order status for the capabilities it declares. | spec-fact | Very high | 2/3 | 2026-07-08 |