biscuits.net
Biscuits from across the UK and the world
Room 03 of 08 · agents and arrivals
Who read us.
Every named machine agent this instrument has recorded, what each was actually sent, and the browser sessions that arrived afterwards from AI answer surfaces.
An agent name is a user-agent claim, not a verified organisation. What protects the figures is behaviour: an agent that breaks the published rules is withdrawn from credit with its history kept visible.
24 NAMED AGENTS1 WITHDRAWN FROM CREDIT2,527 AI-REFERRED SESSIONS53.4 GB SENT TO MACHINES
Section 01
Every named agent, and what each was sent.
One row per agent, every column from the same table and the same window, so the row sums are meaningful. Byte counts are the content actually shipped, not page counts. Amazonbot's row is kept in full and credited nothing.
| Agent | Attempts | Served | No content | Days seen | Anchors | Data sent (MB) | Last seen |
|---|---|---|---|---|---|---|---|
| bingbot | 36,977 | 32,346 | 4,631 | 115 | 6,000 | 13,275.4 | 12 Oct |
| amazonbot withdrawn from credit - history kept in full, nothing credited | 21,796 | 18,803 | 2,993 | 45 | 4,303 | 7,271.5 | 3 Aug |
| perplexitybot | 21,553 | 19,128 | 2,425 | 114 | 4,072 | 6,570.9 | 12 Oct |
| oai-searchbot | 18,457 | 18,014 | 443 | 116 | 4,761 | 5,440.3 | 12 Oct |
| claudebot | 17,210 | 11,839 | 5,371 | 116 | 4,706 | 9,993.0 | 12 Oct |
| meta-externalagent | 13,155 | 8,380 | 4,775 | 112 | 5,648 | 3,776.1 | 12 Oct |
| gptbot | 13,009 | 7,055 | 5,954 | 117 | 5,462 | 1,829.5 | 12 Oct |
| chatgpt-user | 11,816 | 11,012 | 804 | 121 | 2,042 | 4,216.8 | 12 Oct |
| googleother | 7,519 | 3,534 | 3,985 | 96 | 3,079 | 1,360.6 | 12 Oct |
| duckassistbot | 1,552 | 1,507 | 45 | 111 | 913 | 549.3 | 12 Oct |
| bytespider | 1,334 | 1,245 | 89 | 94 | 177 | 369.4 | 12 Oct |
| ccbot | 98 | 79 | 19 | 16 | 93 | 19.9 | 12 Oct |
The 24 agents together: 164,563 attempts, 132,962 served, 53.4 GB sent.Served here counts the raw rule (status + bytes); the credited study figure of 114,159 additionally removes the withdrawn agent.
All 24 named agentsthe long tail, same columns, same window
| Agent | Attempts | Served | No content | Days seen | Anchors | Data sent (MB) | Last seen |
|---|---|---|---|---|---|---|---|
| google-extended | 23 | 4 | 19 | 13 | 17 | 5.3 | 9 Oct |
| cohere | 17 | 2 | 15 | 11 | 13 | 5.5 | 12 Oct |
| youbot | 13 | 2 | 11 | 11 | 11 | 4.2 | 9 Oct |
| claude-user | 9 | 9 | 0 | 4 | 8 | 3.1 | 12 Oct |
| perplexity-user | 6 | 1 | 5 | 5 | 6 | 1.4 | 28 Aug |
| mistral | 4 | 1 | 3 | 4 | 4 | 2.3 | 24 Sep |
| xai-grok | 3 | 0 | 3 | 1 | 3 | 0.0 | 9 Oct |
| grokbot | 3 | 0 | 3 | 3 | 2 | 0.0 | 9 Oct |
| anthropic-ai | 3 | 1 | 2 | 2 | 3 | 2.2 | 1 Aug |
| claude-web | 3 | 0 | 3 | 2 | 3 | 1.0 | 1 Aug |
| generic | 2 | 0 | 2 | 1 | 2 | 0.5 | 5 Oct |
| mistralai-user | 1 | 0 | 1 | 1 | 1 | 0.0 | 6 Oct |
Source: wp_teas_citations grouped by agent - window: 2 Jun 2026 to 12 Oct 2026 - bytes are SUM(bytes_served) - live.
The coverage cross-check - this instrument against the raw access loguntil 7 Aug 2026 capture was gated to AI surfaces, so the raw log sees far more; both are published so the shortfall can be measured
| Agent | Recorded by this instrument | Recorded in the raw access log | Coverage |
|---|---|---|---|
| meta-externalagent | 13,155 | 93,113 | 14.1% |
| gptbot | 13,009 | 91,267 | 14.3% |
| amazonbot | 21,796 | 27,856 | 78.2% |
| claudebot | 17,210 | 10,164 | 169.3% |
| chatgpt-user | 11,816 | 8,921 | 132.5% |
| oai-searchbot | 18,457 | 8,848 | 208.6% |
| googleother | 7,519 | 4,338 | 173.3% |
| bytespider | 1,334 | 3,016 | 44.2% |
| perplexitybot | 21,553 | 2,270 | 949.5% |
| google-extended | 23 | 22 | 104.5% |
Across the frozen log: 3,432,235 requests in total, of which 250,590 were named AI crawlers, 146,034 Googlebot and 21,801 bingbot.Instrument counts are live; the log column is a frozen 7 Aug 2026 reference. A ratio above 100% means capture has outgrown that frozen day.
Section 02
The sessions that actually arrived.
From an AI answer to this shop
AI-referred sessions2,527
Pages viewed in them2,786
Product views299
Baskets started21
Checkouts started16
Completed orders2
Each step is its own evidence class, never derived from the step above. The order count is published because it is the truth.
Strong-match followbacks
53,612
lifetime · 2,843 in the last 7 days
A later request that returned to the exact anchor it was offered, at the strictest match confidence. The strongest evidence our own logs can hold that a read had anywhere to land — still not proof our name appeared in an answer.
Candidate rows examined183,699
Matched to an offer54,837
Matched probably61
Source: wp_teas_sessions (10 May 2026 to 12 Oct 2026) and the followback table (17 Jun 2026 to 12 Oct 2026) - two tables, no shared key, never summed - live.
Section 03
Where the arrivals came from.
| Referring surface | Sessions | Pages viewed | Product pages |
|---|---|---|---|
| ddg-ai | 934 | 983 | 93 |
| chatgpt | 898 | 1,027 | 119 |
| bing-ai | 529 | 574 | 58 |
| copilot | 51 | 55 | 12 |
| brave-ai | 46 | 46 | 9 |
| gemini | 40 | 69 | 6 |
| perplexity | 18 | 18 | 2 |
| kagi | 6 | 6 | 0 |
| claude | 5 | 8 | 0 |
AI-referred sessions only; the surface label is the recorded referrer class.
How strongly each arrival is evidencedverified / probable / possible - the grade travels with the session
| Evidence grade | Sessions | Viewed a product | Started a basket | Orders |
|---|---|---|---|---|
| Verified OpenAI 886 · Microsoft 51 · Google 40 · Perplexity 18 | 1,000 | 111 | 3 | 0 |
| Probable DuckDuckGo 896 · Microsoft 512 · Brave 43 · Kagi 5 | 1,456 | 142 | 3 | 1 |
| Possible DuckDuckGo 38 · Microsoft 17 · Brave 3 · Kagi 1 | 59 | 3 | 0 | 0 |
| Unknown OpenAI 12 | 12 | 7 | 2 | 1 |
Verified: the surface only exists as an AI assistant, or the landing URL carried the assistant's own stamp. Probable: a dual-purpose host, arriving on a citation anchor. Possible: such a host without an anchor. The v5 mint consumes these grades - verified at full weight, probable reduced, possible withheld.
What buyers answered - the customer-declared sourcea separate evidence class, since 2026-09-02, never merged into the referrer counts
| What the buyer said brought them here | Orders |
|---|---|
| duckduckgo | 3 |
| 3 | |
| bing | 1 |
| gemini | 1 |
| social | 1 |
These rows sum to 9 answered orders.
Why most recorded sessions are never called human: the session table classifies every row it has ever written as human, so that label cannot be earned from it. Of 1,613,374 recorded sessions, the overwhelming majority are desktop, one-page visits from scraping floods — recorded across 220 country codes and published as bot pressure, not readership. That is why this room ranks nothing by raw session count and treats only the AI-referred subset as separately evidenced.
Section 04
What was sent, and when.
The same source table across rolling and calendar windows. They overlap, so they must never be added. API reads are a subset of machine reads, not a count of completed tool operations.
Machine traffic: month, fortnight and last 24 hours
Cutoff: , exclusive. Status: available. Last completed projection: 2026-10-12 19:40:37 UTC. These overlapping periods must not be added.
| Period (UTC) | Machine reads | Reads/day | Change | API reads | AI-referred sessions | Verified-source tier |
|---|---|---|---|---|---|---|
| Rolling 30 days 2026-09-12 19:38:00 to 2026-10-12 19:38:00 | 49,841 | 1,661.37 | +184.56% | 4,426 | 507 | 308 |
| Rolling 14 days 2026-09-28 19:38:00 to 2026-10-12 19:38:00 | 17,798 | 1,271.29 | -33.97% | 1,784 | 134 | 111 |
| Rolling 24 hours 2026-10-11 19:38:00 to 2026-10-12 19:38:00 | 1,270 | 1,270.00 | +60.56% | 74 | 10 | 8 |
| Calendar month to date (UTC) 2026-10-01 00:00:00 to 2026-10-12 19:38:00 | 13,851 | 1,172.02 | Not comparable | 1,434 | 110 | 89 |
| Previous calendar month (UTC) 2026-09-01 00:00:00 to 2026-10-01 00:00:00 | 45,615 | 1,520.50 | Not comparable | 3,316 | 734 | 309 |
Reads are retained origin records with status 200/206 and positive bytes, excluding Amazonbot and internal probe records. They do not prove that an answer engine consumed or cited the content. A verified-source referral is a source-evidence tier, not a verified person.
The preceding 30-day and previous-calendar-month periods cross an older status-recording correction, so their raw totals do not support a like-for-like percentage change. Historical session labels are preserved; recent classifier and scrape-gate changes limit comparisons of human traffic.
Full comparison and counting rules · Current snapshot as JSON · Markdown · URSY sponsorship evidence
Daily values, source coverage and limitations
| Date | Reads | Bounds |
|---|---|---|
| 2026-09-28 (partial) | 691 | 2026-09-28 19:38:00 to 2026-09-29 00:00:00 |
| 2026-09-29 | 1,258 | 2026-09-29 00:00:00 to 2026-09-30 00:00:00 |
| 2026-09-30 | 1,998 | 2026-09-30 00:00:00 to 2026-10-01 00:00:00 |
| 2026-10-01 | 2,300 | 2026-10-01 00:00:00 to 2026-10-02 00:00:00 |
| 2026-10-02 | 1,134 | 2026-10-02 00:00:00 to 2026-10-03 00:00:00 |
| 2026-10-03 | 1,180 | 2026-10-03 00:00:00 to 2026-10-04 00:00:00 |
| 2026-10-04 | 943 | 2026-10-04 00:00:00 to 2026-10-05 00:00:00 |
| 2026-10-05 | 1,101 | 2026-10-05 00:00:00 to 2026-10-06 00:00:00 |
| 2026-10-06 | 1,296 | 2026-10-06 00:00:00 to 2026-10-07 00:00:00 |
| 2026-10-07 | 938 | 2026-10-07 00:00:00 to 2026-10-08 00:00:00 |
| 2026-10-08 | 990 | 2026-10-08 00:00:00 to 2026-10-09 00:00:00 |
| 2026-10-09 | 1,096 | 2026-10-09 00:00:00 to 2026-10-10 00:00:00 |
| 2026-10-10 | 878 | 2026-10-10 00:00:00 to 2026-10-11 00:00:00 |
| 2026-10-11 | 853 | 2026-10-11 00:00:00 to 2026-10-12 00:00:00 |
| 2026-10-12 (partial) | 1,142 | 2026-10-12 00:00:00 to 2026-10-12 19:38:00 |
- teas_citations: most recent retained observation before cutoff 2026-10-12 19:36:59.628 UTC; source query completed 2026-10-12 19:40:34 UTC. Counts describe retained origin records. An earliest row or a successful query does not prove uninterrupted collection or edge-cache coverage.
- teas_sessions: most recent retained observation before cutoff 2026-10-12 19:37:47.000 UTC; source query completed 2026-10-12 19:40:37 UTC. Counts describe retained origin records. An earliest row or a successful query does not prove uninterrupted collection or edge-cache coverage.
- Rolling windows overlap and must not be added. All ends are exclusive. Rates use actual elapsed duration.
- Named bot families and browser classes are user-agent claims, not authenticated organisations or verified people.
- API URL reads are a subset of machine reads, not a count of completed tool operations. Mirrored API trace records are not added.
- HEAD and other response-method limitations are exposed separately. Recorded positive bytes are not independent proof of consumption.
- Historical session labels are preserved. The 9 September faceted-scrape gate and 12 September unknown-client correction limit human-traffic comparisons.
- The September AI-referral projection includes the existing 2 September UTM reconstruction; original archives remain separate.
- Read comparisons crossing the 8 August response-status correction are withheld. Earlier raw totals remain visible with partial comparability.
- No count here proves that URSY sponsorship caused traffic, a citation, or a sale.
Section 05
Reading and using are different.
From 6 October 2026 the family list also counts xAI (GrokBot, xAI Grok, Grok DeepSearch; marked claimed because xAI publishes no addresses), Mistral (MistralAI User and MistralAI Index, which we can check against Mistral's published addresses, and MistralAI Training), and Anthropic's Claude User and Claude SearchBot.
Reading and using are different. Crawlers read pages. Assistants connected to our MCP server use tools. Both are listed here, in separate tables, and never added together. The assistants that used our tools in the last 30 days:
| Assistant | Requests | Tool answers | Baskets built |
|---|---|---|---|
| other | 6,656 | 43 | 0 |
| node | 1,431 | 0 | 0 |
| script | 1,336 | 1 | 0 |
| chatgpt | 387 | 342 | 4 |
| claude | 346 | 5 | 0 |
| grok | 333 | 13 | 2 |
| unknown | 51 | 0 | 0 |
| perplexity | 17 | 0 | 0 |
| smithery | 1 | 0 | 0 |
MCP server requests by assistant family, teas.co.uk's own tests left out. Directory testers and scripts appear under their own names.
Source: wp_teas_chatgpt_calls grouped by client family; window: last 30 days; live.
Keep reading
Where this leads next.
One study, one style, eight rooms. The legacy room addresses now land on the room that absorbed their content, and every machine mirror keeps its original path.
What they read
The doors those agents knocked on, the probe-share honesty split and what came back.
Open the record →
The mint & leaderboard
What these reads earn: the board, the classes and the run records behind them.
Open the record →
traffic/data.md
The dated machine-read windows as a markdown twin, for machines.
Open the record →
