{
  "id": "C01",
  "url": "https://cartforagents.com/guides/agent-ready-product-data",
  "title": "Agent-ready product data: build a factual record for each SKU",
  "description": "Record product identity, values, units, test conditions, sources, exclusions and unknowns for each variant. Includes a fill-in template, a worked humidifier record and a page-versus-catalog check.",
  "answer": "Build one record for each variant you sell: what it is, each important value with its unit and the condition it was measured under, where that fact came from, when you last checked it, and what the product is not for. Mark anything you haven't verified as unknown instead of filling the gap. Start with the facts customers ask about most, because those are the facts a shopper's agent will look for.",
  "take": "A record like this is the most useful single asset a spec-sold brand can build for AI shopping: every page, feed and channel can be filled from it. It also closes the gaps we keep finding, like the 6 of 10 humidifier descriptions on one catalog shelf that gave no decibel figure.",
  "summary": "A useful product record says what is true, when it applies and where it came from.",
  "claims": [
    {
      "text": "Shopify says some Global Catalog response fields are generated or enriched by Shopify and marked Inferred, including the product description, technical specifications, top features and selling points. It says they may vary in accuracy and should be treated as discovery signals, not merchant-authored source text.",
      "source_title": "Shopify: Global Catalog MCP, Inferred response fields",
      "source_url": "https://shopify.dev/docs/agents/catalog/global-catalog",
      "source_date": "2026-10-27",
      "method": "documented",
      "limitation": "Living developer documentation; the date is when we checked it, not a publication date. It does not say how the fields are generated or how any assistant uses them."
    },
    {
      "text": "Global Catalog separates discovery (search or lookup, with results clustered into one product and offers from several merchants) from evaluation of a specific product or variant, where options, price and the seller checkout link are retrieved.",
      "source_title": "Shopify: Global Catalog MCP, How it works",
      "source_url": "https://shopify.dev/docs/agents/catalog/global-catalog",
      "source_date": "2026-10-27",
      "method": "documented",
      "limitation": "Describes the catalog interface, not the final choice an assistant shows a shopper."
    },
    {
      "text": "Shopify syndicates eligible products to AI channels with title, description, options, images, price, availability and other key attributes. Catalog Mapping can source product data stored in custom fields such as metafields and metaobjects, and can group separate products as variants of one listing.",
      "source_title": "Shopify Help Center: Shopify Catalog and product discovery for agentic storefronts",
      "source_url": "https://help.shopify.com/en/manual/online-sales-channels/agentic-storefronts/products",
      "source_date": "2026-10-27",
      "method": "documented",
      "limitation": "Living help page checked on this date. It does not promise that every custom field reaches every assistant unchanged."
    },
    {
      "text": "OpenAI says ChatGPT may generate simplified product titles and descriptions, that its feature labels are not guarantees, that merchants are ranked on factors such as availability, price, quality and whether they are the maker or primary seller, and that price or shipping changes may take time to appear.",
      "source_title": "OpenAI Help Center: Shopping with ChatGPT Search",
      "source_url": "https://help.openai.com/en/articles/11128490-shopping-with-chatgpt-search",
      "source_date": "2026-10-27",
      "method": "documented",
      "limitation": "Living help article checked on this date. It lists inputs, not weights, and is not a causal ranking study."
    },
    {
      "text": "For the search \"humidifier for dry winter air large room quiet top fill\", 4 of the 10 product descriptions returned printed a decibel figure (positions 2, 3, 5 and 7), and none of those 4 stated the setting, distance or test method. Three other descriptions described noise in words only, and three made no noise statement. Counting Shopify-generated metadata as well, 6 of the 10 records carried a decibel figure. No title did.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "One search, one unpersonalized snapshot. The 4 counts the description field; the 6 adds Shopify-generated metadata. Counts listings, not market share, and measures what was written, not how loud any unit is."
    },
    {
      "text": "In the same snapshot, one humidifier description said \"up to 32 hours\" while the Shopify-generated specification list in the same record said \"Up to 36 hours\". Another record's generated list gave a maximum room area of 150 m², a value absent from the description we received; 150 also appears in that product's model name.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "We cannot see what Shopify used to generate these fields; the values may come from merchant data we did not receive. Two examples, not a rate of errors."
    },
    {
      "text": "In the snapshot for \"toddler snowsuit rated for minus 30\", one description rated the insulation in the hood to -30°C. The generated specification list in the same record said the insulation was rated to -30°C, without the word hood.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "One record. The full garment rating is unknown to us; we did not inspect the product or the manufacturer documentation."
    },
    {
      "text": "Two listings in that snowsuit result did state -30 °C. Our first text matcher reported them as missing because it did not treat \"minus 30\" and \"-30 °C\" as the same value.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "This is an error in our own tool. It does not show whether any AI shopping agent makes the same mistake."
    },
    {
      "text": "In a supplied-snippet simulation, an invented humidifier was placed among 7 real catalog listings and each model picked 2 of the 8, so chance is 25%. With vague copy it was picked in 3 of 180 sessions across three Claude models, 0 of 60 on GPT-6.1-Sol, 6 of 60 on Gemini 3.8 Flash and 3 of 54 on Gemini 3.1 Pro. With its noise, coverage, tank and runtime facts as a spec line: 134 of 180, 20 of 60, 19 of 59 and 15 of 55. On GPT and Gemini those totals split by shopper context: picked in every session with a detailed shopper brief (20 of 20, 19 of 19, 15 of 15) and in 0 of 120 sessions across those three models (0 of 40 each) with a one-line ask or no shopper. An invented lip gloss went from 0 picks with vague copy on every model to 168 of 180, 60 of 60, 49 of 60 and 53 of 60 when its description stated its facts.",
      "source_title": "Cart for Agents: Vague vs specific product facts, simulated picks by Claude, GPT and Gemini models",
      "source_url": "https://cartforagents.com/research/vague-specific-product-facts-simulation",
      "source_date": "2026-10-27",
      "method": "controlled-simulation",
      "limitation": "Models chose from snippets we supplied, never opened pages and had no tools. The target and its facts were invented, and every model had to pick two, with no \"none fit\" option. The detailed shopper brief was written to fit the test product. API models, not the ChatGPT or Gemini shopping products. Not live visibility, rank or sales."
    },
    {
      "text": "One humidifier description in that result stated a 6.2 L tank, 320 mL/h mist output and up to 62 hours of runtime. At 320 mL/h a 6.2 L tank empties in about 19 hours, so the 62-hour figure implies an average near 100 mL/h, a lower setting the description did not name.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "inferred",
      "limitation": "Arithmetic on the stated figures only (6.2 L / 0.32 L/h). Real output varies with setting, humidity and water level; we did not test the unit."
    },
    {
      "text": "In the snapshot for \"anti theft backpack for city travel\", two catalog records for what appears to be the same 28-litre backpack carried different dimensions. One record's generated specification list gave 19.7 x 11.2 x 7.5 in. The other record's description, and its generated list, gave a height of 11.2 in, width of 7.5 in and depth of 2.4 in.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "We did not confirm the records are the same variant or check either against the manufacturer. It shows a conflict, not which value is correct."
    },
    {
      "text": "Across 162 searches in that snapshot, a product-level rating was absent on 440 of 1,620 returned listings. 106 of those 440 carried a rating on the first returned variant, leaving 334 with neither. No product or variant rating had a count of zero.",
      "source_title": "Cart for Agents: Receipts cited by our guides (Shopify agent-catalog snapshot, Oct 26, 2026)",
      "source_url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "source_date": "2026-10-26",
      "method": "observed",
      "limitation": "Occurrences, not distinct products. An absent rating is unknown: it does not mean zero reviews, and it does not mean nobody supplied a rating anywhere."
    },
    {
      "text": "Google says there are no additional requirements or special optimizations needed to appear in AI Overviews or AI Mode beyond its normal Search best practices.",
      "source_title": "Google Search Central: AI features and your website",
      "source_url": "https://developers.google.com/search/docs/appearance/ai-features",
      "source_date": "2026-10-27",
      "method": "documented",
      "limitation": "Covers Google Search AI features only, checked on this date. It is not a statement about other assistants or about product ranking."
    }
  ],
  "sources": [
    {
      "title": "Shopify: Global Catalog MCP",
      "url": "https://shopify.dev/docs/agents/catalog/global-catalog",
      "accessed": "2026-10-27"
    },
    {
      "title": "Shopify Help Center: Shopify Catalog and product discovery for agentic storefronts",
      "url": "https://help.shopify.com/en/manual/online-sales-channels/agentic-storefronts/products",
      "accessed": "2026-10-27"
    },
    {
      "title": "OpenAI Help Center: Shopping with ChatGPT Search",
      "url": "https://help.openai.com/en/articles/11128490-shopping-with-chatgpt-search",
      "accessed": "2026-10-27"
    },
    {
      "title": "Google Search Central: AI features and your website",
      "url": "https://developers.google.com/search/docs/appearance/ai-features",
      "accessed": "2026-10-27"
    },
    {
      "title": "Cart for Agents: Receipts cited by our guides",
      "url": "https://cartforagents.com/research/agent-shopping-research#receipts-cited-by-our-guides",
      "accessed": "2026-10-27"
    },
    {
      "title": "Cart for Agents: Vague vs specific product facts, simulated picks by Claude, GPT and Gemini models",
      "url": "https://cartforagents.com/research/vague-specific-product-facts-simulation",
      "accessed": "2026-10-27"
    }
  ],
  "limitations": [
    "The catalog examples come from one unpersonalized Shopify agent-catalog snapshot taken on October 26, 2026. They show what was written and received, not how often these patterns occur or how any assistant ranked the products.",
    "We cannot see inside ChatGPT, Gemini, Copilot or any other assistant. Each adds its own sources, rewriting and ranking, so the record you publish is not necessarily the record a shopper sees.",
    "The simulation used supplied snippets, invented products and six API models from three families. It supports disclosing fit facts; it does not predict your rank or sales in any assistant.",
    "A more complete record does not guarantee that a product fits, is safe, or gets picked. It makes a correct match possible and a wrong one easier to catch.",
    "Store names and private catalog receipts are withheld. Quoted excerpts are kept short."
  ],
  "related": [
    "https://cartforagents.com/research/quiet-humidifiers",
    "https://cartforagents.com/research/vague-specific-product-facts-simulation",
    "https://cartforagents.com/research/agent-shopping-research",
    "https://cartforagents.com/guides/spec-sold-product-guides",
    "https://cartforagents.com/guides/humidifier-field-guide"
  ],
  "published": "2026-10-27",
  "updated": "2026-10-27",
  "checked": "2026-10-27",
  "kind": "guide"
}