{
    "id": 1081619,
    "title": "AI attribution: a page read, a visit and an order are different",
    "slug": "ai-attribution",
    "type": "page",
    "url": "https://teas.co.uk/wiki/ai-attribution/",
    "modified": "2026-11-15T08:57:40+00:00",
    "excerpt": "Attribution is the work of connecting an event to a source. For a shop, that might mean identifying the link a visitor followed or the route associated\u2026",
    "content_text": "Attribution is the work of connecting an event to a source. For a shop, that might mean identifying the link a visitor followed or the route associated with an order. It helps explain what the shop can observe, while keeping uncertainty visible.\nWhy a tea shop cares: the shop wants to know whether AI really sells tea, so a page read, a visit and an order are counted separately.\nAn AI system reading a page, a person visiting from an AI answer and a customer buying are three different events.\nStart with the event\nA fetch is a request for information. A server log can show that a response was served. It cannot, on that evidence alone, show what the assistant said to a user.\nA referral is a visit associated with a source link. A session is a group of activity counted under the site's stated rules. A link carrying a source tag can help identify the route; a missing tag does not prove that AI played no part.\nAn order is a separate commerce event. Counts should say whether they mean placed orders, paid orders or orders after refunds, and which dates they cover.\nWhat does conversion mean?\nA conversion rate compares a specified outcome with a specified population, such as paid orders divided by eligible sessions. Change the population or time window and you change the meaning of the rate. A result from another retailer or country is context, not a result measured at teas.co.uk.\nThe crawl-to-refer ratio\nThis compares page requests with visits attributed to the service making them. A high ratio can describe an uneven exchange, but only if both sides have clear definitions and compatible windows. It is not a count of verified recommendations or an estimate of sales by itself.\nWhy not put every number into one total?\nBecause the same journey can produce several events, and some journeys cannot be connected at all. Adding reads, visits and orders would hide the differences and could count the same activity repeatedly.\nteas.co.uk explains its evidence and limits in Under the Hood and what we can prove. When discussing a figure, keep its source, period and definition with it. A dated historical snapshot should remain dated; a live total should be labelled and generated as live.\nThat discipline belongs to the wider truth entity idea. Clear records should help the shop admit what it cannot trace, as well as explain what it can.",
    "contentSignals": "ai-train=yes, search=yes, ai-input=yes",
    "links": {
        "apiCatalog": "https://teas.co.uk/.well-known/api-catalog",
        "llmsTxt": "https://teas.co.uk/llms.txt",
        "mcp": "https://teas.co.uk/mcp",
        "mcpSetupGuides": "https://teas.co.uk/ai/",
        "mcpCard": "https://teas.co.uk/.well-known/mcp/server-card.json",
        "primaryAgenticRouteAuthority": "https://teas.co.uk/.well-known/teas-primary-agentic-route-authority.json"
    }
}