{
  "name": "AgentMint.net Signals Database",
  "version": "v1",
  "description": "The structured catalog of agent-selection signals: why AI shopping agents pick one store, product, or offer over another. Every record is evidence-typed (spec-fact / reported / hypothesis) with a confidence level and, where a platform documents its behavior, per-platform status (honest \"unknown\" otherwise).",
  "funnel_stages": [
    "discovery",
    "matching",
    "comparison",
    "choice"
  ],
  "field_notes": {
    "evidence": "spec-fact (official doc) | reported (named third party) | hypothesis (our inference)",
    "confidence": "very-high | high | medium | low (derived from evidence unless a confidence_note overrides)",
    "impact": "1-3 editorial prioritization (same semantics as the checklist weight)",
    "platforms.*.status": "supported | partial | unsupported | observed | reported | unknown (unknown = undocumented)"
  },
  "signal_count": 32,
  "signals": [
    {
      "id": "sig-acp-readiness",
      "url": "https://agentmint.net/signals/acp-readiness/",
      "name": "ACP feed and checkout readiness",
      "definition": "Whether a store targeting ChatGPT checkout ships the ACP feed with correct eligibility flags and the return fields checkout-eligible items require.",
      "affects": "choice",
      "evidence": "spec-fact",
      "confidence": "very-high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {
        "chatgpt": {
          "status": "supported",
          "source_url": "https://developers.openai.com/commerce/specs/file-upload/products",
          "last_verified": "2026-07-08",
          "note": "ACP is the rail ChatGPT's shopping surfaces read; is_eligible_search=true is a precondition for is_eligible_checkout, and return_policy is required when checkout-eligible."
        }
      },
      "related_checklist_items": [
        "a-protocol-presence-02",
        "a-checkout-ops-05"
      ],
      "related_handbook": [
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-ucp-readiness",
        "sig-validation-hygiene",
        "sig-payment-rail-readiness"
      ],
      "sources": [
        {
          "title": "ACP product feed specification",
          "url": "https://developers.openai.com/commerce/specs/file-upload/products",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "acp",
        "chatgpt-checkout",
        "eligibility-flags",
        "return-fields"
      ],
      "how_to_act": "If you target ChatGPT checkout, enroll in OpenAI's merchant program, set is_eligible_search on products to surface, and set is_eligible_checkout only on rows that also carry return_policy and the required return-window fields."
    },
    {
      "id": "sig-agent-infra-reachability",
      "url": "https://agentmint.net/signals/agent-infra-reachability/",
      "name": "Agent infrastructure reachability",
      "definition": "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.",
      "affects": "discovery",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {
        "chatgpt": {
          "status": "supported",
          "source_url": "https://developers.openai.com/api/docs/bots",
          "last_verified": "2026-07-08",
          "note": "OpenAI publishes verifiable IP/user-agent endpoints (gptbot.json, searchbot.json, chatgpt-user.json) precisely so you can allow-list the real agents."
        }
      },
      "related_checklist_items": [
        "a-bot-access-04",
        "a-monitoring-05",
        "a-monitoring-09"
      ],
      "related_handbook": [
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-crawl-directives",
        "sig-origin-serveability"
      ],
      "sources": [
        {
          "title": "Overview of OpenAI Crawlers",
          "url": "https://developers.openai.com/api/docs/bots",
          "date": "2026-07-08"
        },
        {
          "title": "ACP product feed specification",
          "url": "https://developers.openai.com/commerce/specs/file-upload/products",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "waf",
        "rate-limiting",
        "geoblocking",
        "https",
        "reachability"
      ],
      "how_to_act": "Fetch your own product URL with each vendor's published user-agent and IP range, confirm a 200 (not a challenge), serve everything over HTTPS with no mixed content, and re-test after any WAF or CDN change."
    },
    {
      "id": "sig-agent-monitoring",
      "url": "https://agentmint.net/signals/agent-monitoring/",
      "name": "Agent-readiness monitoring and ownership",
      "definition": "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.",
      "affects": "discovery",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-monitoring-01",
        "a-monitoring-02",
        "a-monitoring-03"
      ],
      "related_handbook": [
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-answer-presence-tracking",
        "sig-validation-hygiene"
      ],
      "sources": [
        {
          "title": "Overview of OpenAI Crawlers",
          "url": "https://developers.openai.com/api/docs/bots",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "log-monitoring",
        "ai-traffic-segmentation",
        "ownership",
        "readiness-cadence"
      ],
      "how_to_act": "Grep access logs for the documented agent user-agents (confirming 200s), isolate AI-assistant referrers in analytics, and assign one named owner a recurring monthly re-check that re-runs the validators."
    },
    {
      "id": "sig-agent-win-rate-measurement",
      "url": "https://agentmint.net/signals/agent-win-rate-measurement/",
      "name": "Defined agent win-rate measurement",
      "definition": "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.",
      "affects": "choice",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-measurement-01",
        "b-measurement-04"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-retest-on-model-updates",
        "sig-position-bias-audit",
        "sig-answer-presence-tracking"
      ],
      "sources": [],
      "topics": [
        "measurement",
        "win-rate",
        "methodology"
      ],
      "how_to_act": "Write a win-rate definition and sample size, run a fixed prompt set against each engine on the same day, and report a range, not a bare point figure."
    },
    {
      "id": "sig-answer-presence-tracking",
      "url": "https://agentmint.net/signals/answer-presence-tracking/",
      "name": "Track AI-answer presence, not just referrals",
      "definition": "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.",
      "affects": "discovery",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-measurement-03"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-agent-win-rate-measurement",
        "sig-agent-monitoring"
      ],
      "sources": [],
      "topics": [
        "measurement",
        "answer-presence",
        "consideration-set"
      ],
      "how_to_act": "For each top category query, log whether every engine names or links your store, tracked over time and separately from referral clicks.",
      "notes": "Discovery-stage measurement (whether engines name you at all), distinct from the choice-stage agent win rate."
    },
    {
      "id": "sig-buyer-question-descriptions",
      "url": "https://agentmint.net/signals/buyer-question-descriptions/",
      "name": "Descriptions answer relayed buyer questions",
      "definition": "Product copy answers, in buyer language, the concrete questions agents relay from users (fit, compatibility, use-case) rather than marketing fluff that dodges them.",
      "affects": "comparison",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-product-content-02"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-facts-per-token",
        "sig-description-rewrite-experiment"
      ],
      "sources": [
        {
          "title": "ACES (arXiv:2508.02630)",
          "url": "https://arxiv.org/abs/2508.02630",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "descriptions",
        "product-content",
        "buyer-questions"
      ],
      "how_to_act": "List the 5 questions buyers ask (fit, compatibility, use-case) and confirm the description answers each in plain sentences, mirroring key facts out of any spec-only table."
    },
    {
      "id": "sig-content-equivalence-no-cloaking",
      "url": "https://agentmint.net/signals/content-equivalence-no-cloaking/",
      "name": "Content equivalence (no cloaking)",
      "definition": "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.",
      "affects": "discovery",
      "evidence": "spec-fact",
      "confidence": "very-high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {
        "copilot": {
          "status": "reported",
          "source_url": "https://www.bing.com/webmasters/help/webmaster-guidelines-30fba23a",
          "last_verified": "2026-07-08",
          "note": "Bing's current Webmaster Guidelines list cloaking among practices that reduce ranking eligibility and grounding visibility across Bing and Copilot experiences."
        }
      },
      "related_checklist_items": [
        "b-price-position-02",
        "b-product-content-05"
      ],
      "related_handbook": [
        "handbook/information-density",
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-machine-readable-mirror",
        "sig-price-competitive-awareness",
        "sig-origin-serveability"
      ],
      "sources": [
        {
          "title": "Google, Spam policies for Google web search",
          "url": "https://developers.google.com/search/docs/essentials/spam-policies"
        },
        {
          "title": "MDN, HTTP content negotiation",
          "url": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Content_negotiation"
        },
        {
          "title": "Bing, Webmaster Guidelines",
          "url": "https://www.bing.com/webmasters/help/webmaster-guidelines-30fba23a"
        },
        {
          "title": "Bing Webmaster Blog",
          "url": "https://blogs.bing.com/webmaster/october-2018/bingbot-Series-JavaScript,-Dynamic-Rendering,-and-Cloaking-Oh-My",
          "date": "2018-10-31"
        }
      ],
      "topics": [
        "cloaking",
        "content-negotiation",
        "spam-policy",
        "trust"
      ],
      "how_to_act": "Keep the facts identical across HTML, Markdown, .md mirror, and feed; never vary the content itself by user-agent (throttling a request is access control, not cloaking)."
    },
    {
      "id": "sig-crawl-directives",
      "url": "https://agentmint.net/signals/crawl-directives/",
      "name": "Crawl directives (robots.txt + sitemap)",
      "definition": "Whether your robots.txt and XML sitemap let AI search and citation crawlers find and reach your product URLs at all.",
      "affects": "discovery",
      "evidence": "spec-fact",
      "confidence": "very-high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {
        "chatgpt": {
          "status": "supported",
          "source_url": "https://developers.openai.com/api/docs/bots",
          "last_verified": "2026-07-08",
          "note": "OpenAI states that disallowing OAI-SearchBot means you will not be shown in ChatGPT search answers; the search crawler honors robots.txt."
        }
      },
      "related_checklist_items": [
        "a-bot-access-01",
        "a-bot-access-02",
        "a-bot-access-03",
        "a-monitoring-04"
      ],
      "related_handbook": [
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-agent-infra-reachability",
        "sig-origin-serveability",
        "sig-agent-monitoring"
      ],
      "sources": [
        {
          "title": "Overview of OpenAI Crawlers",
          "url": "https://developers.openai.com/api/docs/bots",
          "date": "2026-07-08"
        },
        {
          "title": "Google's common crawlers",
          "url": "https://developers.google.com/crawling/docs/crawlers-fetchers/google-common-crawlers",
          "date": "2026-07-08"
        },
        {
          "title": "Rankly UCP/ACP validator",
          "url": "https://tryrankly.com/ucp-validator",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "robots-txt",
        "sitemap",
        "crawlers",
        "discovery"
      ],
      "how_to_act": "Allow the named search/citation crawlers in robots.txt, decide training tokens (GPTBot, Google-Extended) deliberately, and keep an accessible current XML sitemap of live product URLs."
    },
    {
      "id": "sig-crawlable-content",
      "url": "https://agentmint.net/signals/crawlable-content/",
      "name": "Server-rendered, crawlable content",
      "definition": "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.",
      "affects": "matching",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-bot-access-05",
        "a-monitoring-08",
        "b-trust-policy-03"
      ],
      "related_handbook": [
        "handbook/serving-agent-traffic",
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-offer-markup-completeness",
        "sig-facts-per-token",
        "sig-returns-legibility"
      ],
      "sources": [
        {
          "title": "ucptools.dev: UCP/ACP validator",
          "url": "https://ucptools.dev",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "ssr",
        "javascript",
        "crawlable-html",
        "policy-pages",
        "rendering"
      ],
      "how_to_act": "Load the product and policy pages with JavaScript disabled (view source, not devtools) and confirm title, price, availability, description, and full policy text are all present in the raw response."
    },
    {
      "id": "sig-delivery-eta-legibility",
      "url": "https://agentmint.net/signals/delivery-eta-legibility/",
      "name": "Delivery ETA is computable per destination",
      "definition": "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.",
      "affects": "comparison",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-delivery-returns-01",
        "b-delivery-returns-03",
        "b-delivery-returns-09"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-offer-cost-legibility",
        "sig-returns-legibility",
        "sig-offer-consistency-freshness"
      ],
      "sources": [
        {
          "title": "Google: Shipping policy structured data",
          "url": "https://developers.google.com/search/docs/appearance/structured-data/shipping-policy",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "delivery",
        "shipping",
        "eta",
        "cutoff-time"
      ],
      "how_to_act": "Set handlingTime, transitTime and cutoffTime as ranges (siblings, not nested) with per-destination transit, and echo the estimate in PDP text so a distinct ETA resolves for two distant ZIPs."
    },
    {
      "id": "sig-description-rewrite-experiment",
      "url": "https://agentmint.net/signals/description-rewrite-experiment/",
      "name": "Query-conditional rewrites are a targeted experiment",
      "definition": "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.",
      "affects": "comparison",
      "evidence": "reported",
      "confidence": "high",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-product-content-05"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-buyer-question-descriptions",
        "sig-agent-win-rate-measurement",
        "sig-content-equivalence-no-cloaking"
      ],
      "sources": [
        {
          "title": "ACES (arXiv:2508.02630)",
          "url": "https://arxiv.org/abs/2508.02630",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "descriptions",
        "experiment",
        "aces",
        "win-rate"
      ],
      "how_to_act": "Rewrite a small batch of candidate SKUs (same facts, no new claims), measure win rate per engine before and after, and serve identical copy to bots and humans.",
      "notes": "Based on ACES (arXiv:2508.02630), a controlled agent-shopping simulation, not measured real-world sales."
    },
    {
      "id": "sig-endorsement-not-sponsored",
      "url": "https://agentmint.net/signals/endorsement-not-sponsored/",
      "name": "Earn endorsement, never self-label sponsored",
      "definition": "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.",
      "affects": "choice",
      "evidence": "reported",
      "confidence": "high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-product-content-06",
        "b-trust-policy-04"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-review-depth",
        "sig-seller-identity-reachable",
        "sig-content-equivalence-no-cloaking"
      ],
      "sources": [
        {
          "title": "ACES (arXiv:2508.02630)",
          "url": "https://arxiv.org/abs/2508.02630",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "endorsement",
        "sponsored",
        "badges",
        "trust",
        "aces"
      ],
      "how_to_act": "Remove any self-applied sponsored/ad styling from agent-visible pages and pursue only endorsement or verified-seller programs you genuinely qualify for.",
      "notes": "Based on ACES (arXiv:2508.02630), a controlled agent-shopping simulation, not measured real-world sales."
    },
    {
      "id": "sig-facts-per-token",
      "url": "https://agentmint.net/signals/facts-per-token/",
      "name": "Facts per token, complete against peers",
      "definition": "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.",
      "affects": "comparison",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-product-content-01",
        "b-product-content-03"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-buyer-question-descriptions",
        "sig-variant-and-title-matching",
        "sig-machine-readable-mirror"
      ],
      "sources": [
        {
          "title": "Vercel: Making agent-friendly pages with content negotiation",
          "url": "https://vercel.com/blog/making-agent-friendly-pages-with-content-negotiation",
          "date": "2026-02-03"
        },
        {
          "title": "Cloudflare, Markdown for Agents",
          "url": "https://developers.cloudflare.com/fundamentals/reference/markdown-for-agents/",
          "date": "approx. 2026-06-05"
        }
      ],
      "topics": [
        "token-economy",
        "facts-per-token",
        "completeness",
        "specificity",
        "machine-readability"
      ],
      "how_to_act": "Lead every machine surface with specs, price, GTIN, availability, and policy; list the attributes the top 3 competing listings expose and fill your gaps truthfully with measurable facts, not superlatives."
    },
    {
      "id": "sig-guest-checkout",
      "url": "https://agentmint.net/signals/guest-checkout/",
      "name": "Guest checkout completability",
      "definition": "Whether an agent with no account credentials can complete a purchase, because no forced signup, password, or email verification blocks the path.",
      "affects": "choice",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-checkout-ops-01"
      ],
      "related_handbook": [
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-payment-rail-readiness",
        "sig-acp-readiness"
      ],
      "sources": [],
      "topics": [
        "guest-checkout",
        "account-creation",
        "checkout-completion"
      ],
      "how_to_act": "Confirm a first-time buyer can reach order confirmation entering only shipping and payment, with any account-creation prompt deferred to after the order is placed."
    },
    {
      "id": "sig-llms-txt-priority-order",
      "url": "https://agentmint.net/signals/llms-txt-priority-order/",
      "name": "llms.txt priority ordering",
      "definition": "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.",
      "affects": "discovery",
      "evidence": "spec-fact",
      "confidence": "very-high",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-machine-readable-mirror",
        "sig-facts-per-token"
      ],
      "sources": [
        {
          "title": "llms.txt proposal, llmstxt.org",
          "url": "https://llmstxt.org"
        }
      ],
      "topics": [
        "llms-txt",
        "prioritization",
        "machine-index"
      ],
      "how_to_act": "Put the buying-relevant pages above the 'Optional' section and order each link list by decision weight, not by navigation or site-map convenience."
    },
    {
      "id": "sig-machine-readable-mirror",
      "url": "https://agentmint.net/signals/machine-readable-mirror/",
      "name": "Machine-readable page representation",
      "definition": "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.",
      "affects": "discovery",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-facts-per-token",
        "sig-content-equivalence-no-cloaking",
        "sig-llms-txt-priority-order"
      ],
      "sources": [
        {
          "title": "Vercel, Making agent-friendly pages with content negotiation",
          "url": "https://vercel.com/blog/making-agent-friendly-pages-with-content-negotiation",
          "date": "2026-02-03"
        },
        {
          "title": "Pronovix, How to serve Markdown to AI agents",
          "url": "https://pronovix.com/articles/how-serve-markdown-ai-agents-without-breaking-your-seo",
          "date": "2026-03-24"
        },
        {
          "title": "MDN, HTTP content negotiation",
          "url": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Content_negotiation"
        },
        {
          "title": "Mintlify, Cloudflare, and Vercel agent-Markdown guides",
          "url": "https://mintlify.com/blog/context-for-agents",
          "date": "2026-01-29"
        },
        {
          "title": "Google, Optimizing your website for generative AI features on Google Search",
          "url": "https://developers.google.com/search/docs/fundamentals/ai-optimization-guide"
        }
      ],
      "topics": [
        "content-negotiation",
        "markdown-mirror",
        "rel-alternate"
      ],
      "how_to_act": "Ship a .md mirror or Accept negotiation with a rel=alternate hint and a canonical on the HTML, but do not attribute a selection outcome to it."
    },
    {
      "id": "sig-model-specific-price-sensitivity",
      "url": "https://agentmint.net/signals/model-specific-price-sensitivity/",
      "name": "Price sensitivity varies by model",
      "definition": "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.",
      "affects": "choice",
      "evidence": "reported",
      "confidence": "high",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-price-position-03"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-price-competitive-awareness",
        "sig-agent-win-rate-measurement",
        "sig-retest-on-model-updates"
      ],
      "sources": [
        {
          "title": "ACES (arXiv:2508.02630)",
          "url": "https://arxiv.org/abs/2508.02630",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "price-elasticity",
        "per-model",
        "aces",
        "win-rate"
      ],
      "how_to_act": "Test any price change isolated to one engine and compare that engine's before/after win rate, re-checking sensitivity after major model updates.",
      "notes": "Based on ACES (arXiv:2508.02630), a controlled agent-shopping simulation, not measured real-world sales."
    },
    {
      "id": "sig-offer-consistency-freshness",
      "url": "https://agentmint.net/signals/offer-consistency-freshness/",
      "name": "Offer consistency and freshness across surfaces",
      "definition": "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.",
      "affects": "choice",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-structured-data-04",
        "a-structured-data-02",
        "a-checkout-ops-02",
        "a-checkout-ops-03",
        "b-delivery-returns-08"
      ],
      "related_handbook": [
        "handbook/information-density",
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-offer-markup-completeness",
        "sig-offer-cost-legibility",
        "sig-origin-serveability"
      ],
      "sources": [
        {
          "title": "Product data specification",
          "url": "https://support.google.com/merchants/answer/7052112",
          "date": "2026-07-08"
        },
        {
          "title": "Get started with the Agentic Commerce Protocol",
          "url": "https://developers.openai.com/commerce/guides/get-started",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "price-parity",
        "freshness",
        "data-consistency",
        "inventory-sync",
        "trust"
      ],
      "how_to_act": "Drive price, availability, shipping, and return values from one source so all surfaces match, keep the feed's required attributes current, and put price and availability on a short TTL (or bypass the cache) so a stale offer never reaches an agent."
    },
    {
      "id": "sig-offer-cost-legibility",
      "url": "https://agentmint.net/signals/offer-cost-legibility/",
      "name": "Offer cost legibility",
      "definition": "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.",
      "affects": "comparison",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-offer-legibility-01",
        "b-offer-legibility-03",
        "b-offer-legibility-04",
        "b-offer-legibility-05",
        "b-offer-legibility-06",
        "b-delivery-returns-02",
        "b-delivery-returns-10"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-price-competitive-awareness",
        "sig-delivery-eta-legibility",
        "sig-offer-consistency-freshness"
      ],
      "sources": [
        {
          "title": "Google: Shipping policy structured data",
          "url": "https://developers.google.com/search/docs/appearance/structured-data/shipping-policy",
          "date": "2026-07-08"
        },
        {
          "title": "Google: Merchant listing structured data",
          "url": "https://developers.google.com/search/docs/appearance/structured-data/merchant-listing",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "pricing",
        "shipping-cost",
        "unit-price",
        "sale-price",
        "tax",
        "offer-legibility"
      ],
      "how_to_act": "With images suppressed, confirm the current price, sale window (priceValidUntil), currency, tax treatment, shipping, fees, unit price, and free-shipping threshold are all present as real numbers and match checkout."
    },
    {
      "id": "sig-offer-markup-completeness",
      "url": "https://agentmint.net/signals/offer-markup-completeness/",
      "name": "Offer markup completeness and truthfulness",
      "definition": "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.",
      "affects": "matching",
      "evidence": "spec-fact",
      "confidence": "very-high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-structured-data-01",
        "a-structured-data-02",
        "a-structured-data-06",
        "a-monitoring-06",
        "a-monitoring-07"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-product-identity",
        "sig-offer-consistency-freshness",
        "sig-validation-hygiene"
      ],
      "sources": [
        {
          "title": "Merchant listing structured data",
          "url": "https://developers.google.com/search/docs/appearance/structured-data/merchant-listing",
          "date": "2026-07-08"
        },
        {
          "title": "Product data specification",
          "url": "https://support.google.com/merchants/answer/7052112",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "json-ld",
        "offer",
        "availability",
        "item-condition",
        "images"
      ],
      "how_to_act": "Ship Product/Offer JSON-LD with price greater than zero in ISO 4217 currency, availability and itemCondition kept truthful to the page, a high-resolution image, and hasMerchantReturnPolicy/shippingDetails objects present and parsing error-free."
    },
    {
      "id": "sig-origin-serveability",
      "url": "https://agentmint.net/signals/origin-serveability/",
      "name": "Origin serve-ability for agents",
      "definition": "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.",
      "affects": "discovery",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-bot-access-04",
        "a-bot-access-03",
        "a-monitoring-01"
      ],
      "related_handbook": [
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-agent-infra-reachability",
        "sig-crawl-directives",
        "sig-offer-consistency-freshness"
      ],
      "sources": [
        {
          "title": "Cloudflare Radar 2025 Year in Review",
          "url": "https://blog.cloudflare.com/radar-2025-year-in-review/",
          "date": "2025-12-15"
        },
        {
          "title": "Cloudflare, Cache revalidation",
          "url": "https://developers.cloudflare.com/cache/concepts/revalidation/"
        },
        {
          "title": "nginx, ngx_http_proxy_module",
          "url": "https://nginx.org/en/docs/http/ngx_http_proxy_module.html"
        },
        {
          "title": "Wikimedia Diff, Mueller, Danis and Lavagetto",
          "url": "https://diff.wikimedia.org/2025/04/01/how-crawlers-impact-the-operations-of-the-wikimedia-projects/",
          "date": "2025-04-01"
        },
        {
          "title": "404 Media, Jason Koebler",
          "url": "https://404media.co/anthropic-ai-scraper-hits-ifixits-website-a-million-times-in-a-day/",
          "date": "2024-07-24"
        },
        {
          "title": "Read the Docs, Eric Holscher",
          "url": "https://about.readthedocs.com/blog/2024/07/ai-crawlers-abuse/",
          "date": "2024-07-25"
        }
      ],
      "topics": [
        "edge-caching",
        "crawler-load",
        "bot-verification",
        "availability"
      ],
      "how_to_act": "Edge-cache the near-static machine surfaces (llms.txt, Markdown mirrors, feeds, mostly-static product pages) with stale-while-revalidate, and allowlist verified bots while rate-limiting only unverified spoofers."
    },
    {
      "id": "sig-payment-rail-readiness",
      "url": "https://agentmint.net/signals/payment-rail-readiness/",
      "name": "Agent-payment rail readiness",
      "definition": "Whether your payment stack can complete an agent-initiated purchase over rails like AP2, Visa Trusted Agent Protocol, or Mastercard Agent Pay.",
      "affects": "choice",
      "evidence": "reported",
      "confidence": "high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-protocol-presence-04"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-acp-readiness",
        "sig-ucp-readiness",
        "sig-guest-checkout"
      ],
      "sources": [
        {
          "title": "AP2: Agent Payments Protocol",
          "url": "https://ap2-protocol.org",
          "date": "2026-07-07"
        }
      ],
      "topics": [
        "ap2",
        "visa-trusted-agent",
        "mastercard-agent-pay",
        "payment-rails"
      ],
      "how_to_act": "Ask your payment provider in writing which agent-payment rails your account supports today, record the dated answer, and re-confirm periodically since support is still evolving.",
      "notes": "These rails gate purchase completability (selectability), not the comparison itself."
    },
    {
      "id": "sig-position-bias-audit",
      "url": "https://agentmint.net/signals/position-bias-audit/",
      "name": "Audit grid position bias per provider",
      "definition": "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.",
      "affects": "choice",
      "evidence": "reported",
      "confidence": "high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-measurement-05"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-agent-win-rate-measurement",
        "sig-retest-on-model-updates"
      ],
      "sources": [
        {
          "title": "ACES (arXiv:2508.02630)",
          "url": "https://arxiv.org/abs/2508.02630",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "measurement",
        "position-bias",
        "grid-layout",
        "aces"
      ],
      "how_to_act": "When results render as a grid, record your on-screen position per engine alongside the win/no-win result and look for correlation with signals you changed.",
      "notes": "Based on ACES (arXiv:2508.02630), a controlled agent-shopping simulation, not measured real-world sales."
    },
    {
      "id": "sig-price-competitive-awareness",
      "url": "https://agentmint.net/signals/price-competitive-awareness/",
      "name": "Competitive price awareness with parity",
      "definition": "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.",
      "affects": "comparison",
      "evidence": "reported",
      "confidence": "high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-price-position-01",
        "b-price-position-02"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-model-specific-price-sensitivity",
        "sig-offer-cost-legibility",
        "sig-content-equivalence-no-cloaking"
      ],
      "sources": [
        {
          "title": "ACES (arXiv:2508.02630)",
          "url": "https://arxiv.org/abs/2508.02630",
          "date": "2026-07-08"
        },
        {
          "title": "Google: Merchant Center product data spec",
          "url": "https://support.google.com/merchants/answer/7052112",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "price-position",
        "competitive-monitoring",
        "parity",
        "anti-cloaking"
      ],
      "how_to_act": "Track your landed cost vs 3-5 competitor totals for your top queries on a fixed cadence, and spot-check that agent-visible and human-visible prices match exactly.",
      "notes": "Based on ACES (arXiv:2508.02630), a controlled agent-shopping simulation, not measured real-world sales."
    },
    {
      "id": "sig-product-identity",
      "url": "https://agentmint.net/signals/product-identity/",
      "name": "Product identity and canonical URL",
      "definition": "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.",
      "affects": "matching",
      "evidence": "spec-fact",
      "confidence": "very-high",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-bot-access-06",
        "a-structured-data-03"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-offer-markup-completeness",
        "sig-validation-hygiene"
      ],
      "sources": [
        {
          "title": "Merchant listing structured data",
          "url": "https://developers.google.com/search/docs/appearance/structured-data/merchant-listing",
          "date": "2026-07-08"
        },
        {
          "title": "Product data specification",
          "url": "https://support.google.com/merchants/answer/7052112",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "canonical-url",
        "gtin",
        "brand",
        "mpn",
        "product-matching"
      ],
      "how_to_act": "Give each product one canonical URL that resolves to the purchasable page and matches the feed link, and populate gtin/brand/mpn wherever a real identifier exists (never invent one)."
    },
    {
      "id": "sig-retest-on-model-updates",
      "url": "https://agentmint.net/signals/retest-on-model-updates/",
      "name": "Re-test after every major model update",
      "definition": "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.",
      "affects": "choice",
      "evidence": "reported",
      "confidence": "high",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-measurement-02"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-agent-win-rate-measurement",
        "sig-position-bias-audit",
        "sig-model-specific-price-sensitivity"
      ],
      "sources": [
        {
          "title": "ACES (arXiv:2508.02630)",
          "url": "https://arxiv.org/abs/2508.02630",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "measurement",
        "model-updates",
        "re-testing",
        "aces"
      ],
      "how_to_act": "Track each engine's current model version and re-run the win-rate protocol within a fixed window whenever a major update lands, comparing against the last baseline.",
      "notes": "Based on ACES (arXiv:2508.02630), a controlled agent-shopping simulation, not measured real-world sales."
    },
    {
      "id": "sig-returns-legibility",
      "url": "https://agentmint.net/signals/returns-legibility/",
      "name": "Return terms are fully legible",
      "definition": "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.",
      "affects": "comparison",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-delivery-returns-04",
        "b-delivery-returns-05",
        "b-delivery-returns-06",
        "b-delivery-returns-07"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-delivery-eta-legibility",
        "sig-crawlable-content",
        "sig-offer-consistency-freshness"
      ],
      "sources": [
        {
          "title": "Google: Return policy structured data",
          "url": "https://developers.google.com/search/docs/appearance/structured-data/return-policy",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "returns",
        "refunds",
        "policy-legibility"
      ],
      "how_to_act": "State the return window, cost/who-pays, method and refund type in prose, and keep each equal to its markup field (merchantReturnDays, returnFees, returnMethod, refundType)."
    },
    {
      "id": "sig-review-depth",
      "url": "https://agentmint.net/signals/review-depth/",
      "name": "Review depth: count, recency, distribution",
      "definition": "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.",
      "affects": "choice",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 3,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-trust-policy-01",
        "b-trust-policy-05"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-endorsement-not-sponsored",
        "sig-seller-identity-reachable"
      ],
      "sources": [
        {
          "title": "ACES (arXiv:2508.02630)",
          "url": "https://arxiv.org/abs/2508.02630",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "reviews",
        "ratings",
        "trust",
        "aces"
      ],
      "how_to_act": "Show a truthful review count, a rolling recent-reviews figure, and a per-star breakdown near the average, with reviewCount and dated Review entries in markup."
    },
    {
      "id": "sig-seller-identity-reachable",
      "url": "https://agentmint.net/signals/seller-identity-reachable/",
      "name": "Seller identity reachable in two hops",
      "definition": "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.",
      "affects": "choice",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-trust-policy-02"
      ],
      "related_handbook": [],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-review-depth",
        "sig-endorsement-not-sponsored",
        "sig-crawlable-content"
      ],
      "sources": [],
      "topics": [
        "trust",
        "identity",
        "organization-schema",
        "contact"
      ],
      "how_to_act": "Ensure business name, address and a contact method are reachable in two hops from a PDP and mirrored in Organization schema site-wide."
    },
    {
      "id": "sig-ucp-readiness",
      "url": "https://agentmint.net/signals/ucp-readiness/",
      "name": "UCP profile and order-management readiness",
      "definition": "Whether a store targeting Google/UCP surfaces publishes a public /.well-known/ucp profile and can return order status for the capabilities it declares.",
      "affects": "choice",
      "evidence": "spec-fact",
      "confidence": "very-high",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {
        "gemini": {
          "status": "supported",
          "source_url": "https://developers.google.com/merchant/ucp",
          "last_verified": "2026-07-08",
          "note": "UCP is the protocol Google's shopping/Gemini surfaces read; the profile at /.well-known/ucp must be publicly accessible without authentication."
        }
      },
      "related_checklist_items": [
        "a-protocol-presence-01",
        "a-checkout-ops-04"
      ],
      "related_handbook": [
        "handbook/serving-agent-traffic"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-acp-readiness",
        "sig-validation-hygiene",
        "sig-payment-rail-readiness"
      ],
      "sources": [
        {
          "title": "UCP business profile guide",
          "url": "https://developers.google.com/merchant/ucp/guides/ucp-profile",
          "date": "2026-07-08"
        },
        {
          "title": "Google: Universal Commerce Protocol developer guide",
          "url": "https://developers.google.com/merchant/ucp",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "ucp",
        "well-known",
        "order-management",
        "protocol-presence"
      ],
      "how_to_act": "If you target Google/UCP surfaces, publish an unauthenticated /.well-known/ucp profile with real capabilities and signing keys, and back any declared order-management capability with a retrievable status endpoint."
    },
    {
      "id": "sig-validation-hygiene",
      "url": "https://agentmint.net/signals/validation-hygiene/",
      "name": "Validation hygiene (use existing validators)",
      "definition": "Whether structured data, feeds, and protocol manifests are run through existing maintained validators rather than a homegrown checker.",
      "affects": "matching",
      "evidence": "spec-fact",
      "confidence": "very-high",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "a-structured-data-05",
        "a-protocol-presence-03"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-offer-markup-completeness",
        "sig-ucp-readiness",
        "sig-acp-readiness"
      ],
      "sources": [
        {
          "title": "Merchant listing structured data",
          "url": "https://developers.google.com/search/docs/appearance/structured-data/merchant-listing",
          "date": "2026-07-08"
        },
        {
          "title": "ucptools.dev: UCP/ACP validator",
          "url": "https://ucptools.dev",
          "date": "2026-07-08"
        }
      ],
      "topics": [
        "validation",
        "rich-results-test",
        "merchant-center-diagnostics",
        "ucp-validator"
      ],
      "how_to_act": "Run the Rich Results Test, Schema.org validator, Merchant Center diagnostics, and a maintained UCP/ACP validator on every deploy; fix every error, then triage warnings."
    },
    {
      "id": "sig-variant-and-title-matching",
      "url": "https://agentmint.net/signals/variant-and-title-matching/",
      "name": "Variants and titles use the words shoppers type",
      "definition": "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.",
      "affects": "matching",
      "evidence": "hypothesis",
      "confidence": "low",
      "impact": 2,
      "status": "active",
      "last_verified": "2026-07-08",
      "platforms": {},
      "related_checklist_items": [
        "b-offer-legibility-02",
        "b-product-content-04"
      ],
      "related_handbook": [
        "handbook/information-density"
      ],
      "related_experiments": [],
      "related_open_questions": [],
      "related_signals": [
        "sig-facts-per-token",
        "sig-buyer-question-descriptions"
      ],
      "sources": [],
      "topics": [
        "titles",
        "variants",
        "query-matching",
        "attributes"
      ],
      "how_to_act": "Read variant names and titles cold: rewrite any that don't lead with the literal attribute or category phrase a shopper would search."
    }
  ]
}