Autumn Sale: 20% off almost everything until 15 NovemberSee the sale

Room 03 of 07 · 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 What protects the figures is behaviour: an agent that breaks the published rules is withdrawn from credit with its history kept visible.

19 NAMED AGENTS1 WITHDRAWN FROM CREDIT2,265 AI-REFERRED SESSIONS41.7 GB SENT TO MACHINES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.

AgentAttemptsServedNo contentDays seenAnchorsData sent (MB)Last seen
bingbot24,92821,2593,669923,8139,374.219 Sep
amazonbot
withdrawn from credit - history kept in full, nothing credited
21,79618,8032,993454,3037,271.53 Aug
claudebot14,6269,7464,880933,5329,331.419 Sep
oai-searchbot13,26312,848415933,4124,155.519 Sep
gptbot11,2995,4125,887945,2931,305.719 Sep
meta-externalagent11,2476,5684,679894,9093,217.919 Sep
perplexitybot10,4748,1492,325912,7582,751.819 Sep
chatgpt-user10,1069,320786981,6713,609.719 Sep
googleother6,7432,7643,979772,5991,135.119 Sep
duckassistbot8438113288515301.319 Sep
bytespider8207408071130197.019 Sep
ccbot88781088617.013 Sep
The 19 agents together: 126,273 attempts, 96,505 served, 41.7 GB sent.Served here counts the raw rule (status + bytes); the credited study figure of 77,702 additionally removes the withdrawn agent.
All 19 named agentsthe long tail, same columns, same window
AgentAttemptsServedNo contentDays seenAnchorsData sent (MB)Last seen
google-extended183159143.217 Sep
perplexity-user615561.428 Aug
youbot514451.616 Sep
cohere404341.017 Sep
anthropic-ai312232.21 Aug
claude-web303231.01 Aug
mistral110111.612 Sep

Source: wp_teas_citations grouped by agent - window: 2 Jun 2026 to 19 Sep 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
AgentRecorded by this instrumentRecorded in the raw access logCoverage
meta-externalagent11,24793,11312.1%
gptbot11,29991,26712.4%
amazonbot21,79627,85678.2%
claudebot14,62610,164143.9%
chatgpt-user10,1068,921113.3%
oai-searchbot13,2638,848149.9%
googleother6,7434,338155.4%
bytespider8203,01627.2%
perplexitybot10,4742,270461.4%
google-extended182281.8%
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 sessions2,265
Pages viewed in them2,398
Product views248
Baskets started11
Checkouts started7
Completed orders1
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
41,152
lifetime · 7,876 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 examined145,218
Matched to an offer42,349
Matched probably61

Source: wp_teas_sessions (10 May 2026 to 19 Sep 2026) and the followback table (17 Jun 2026 to 19 Sep 2026) - two tables, no shared key, never summed - live.

Section 03

Where the arrivals came from.

Referring surfaceSessionsPages viewedProduct pages
ddg-ai93498393
chatgpt69673178
bing-ai52957458
copilot454910
brave-ai33337
gemini12121
perplexity991
claude440
kagi330
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 gradeSessionsViewed a productStarted a basketOrders
Verified
OpenAI 696 · Microsoft 45 · Google 12 · Perplexity 9
7668500
Probable
DuckDuckGo 896 · Microsoft 512 · Brave 31 · Kagi 2
1,44114031
Possible
DuckDuckGo 38 · Microsoft 17 · Brave 2 · Kagi 1
58300

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 hereOrders
duckduckgo2
social1
These rows sum to 3 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 1,547,654 recorded sessions, the overwhelming majority are desktop, one-page visits from scraping floods — recorded across 219 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: 2026-09-19 08:10:28 UTC. These overlapping periods must not be added.

One source snapshot; changes compare equal preceding periods
Period (UTC)Machine readsReads/dayChangeAPI readsAI-referred sessionsVerified-source tier
Rolling 30 days
2026-08-20 08:08:00 to 2026-09-19 08:08:00
27,484916.13Not comparable1,090805210
Rolling 14 days
2026-09-05 08:08:00 to 2026-09-19 08:08:00
19,2961,378.29+176.17%834464132
Rolling 24 hours
2026-09-18 08:08:00 to 2026-09-19 08:08:00
3,6743,674.00+12.05%3163810
Calendar month to date (UTC)
2026-09-01 00:00:00 to 2026-09-19 08:08:00
23,0601,257.44Not comparable907582164
Previous calendar month (UTC)
2026-08-01 00:00:00 to 2026-09-01 00:00:00
20,823671.71Not comparable1,077844308

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

Recorded machine reads across the exact rolling fortnight. The first and last UTC dates can be partial.
2026-09-05: 830 (partial day)09-052026-09-06: 1,07109-062026-09-07: 1,12909-072026-09-08: 34509-082026-09-09: 43009-092026-09-10: 68809-102026-09-11: 90909-112026-09-12: 51009-122026-09-13: 1,38309-132026-09-14: 3,71709-142026-09-15: 50909-152026-09-16: 51109-162026-09-17: 84609-172026-09-18: 4,55709-182026-09-19: 1,861 (partial day)09-19
Daily values, source coverage and limitations
Clipped UTC daily buckets — the sum equals rolling 14-day reads
DateReadsBounds
2026-09-05 (partial)8302026-09-05 08:08:00 to 2026-09-06 00:00:00
2026-09-061,0712026-09-06 00:00:00 to 2026-09-07 00:00:00
2026-09-071,1292026-09-07 00:00:00 to 2026-09-08 00:00:00
2026-09-083452026-09-08 00:00:00 to 2026-09-09 00:00:00
2026-09-094302026-09-09 00:00:00 to 2026-09-10 00:00:00
2026-09-106882026-09-10 00:00:00 to 2026-09-11 00:00:00
2026-09-119092026-09-11 00:00:00 to 2026-09-12 00:00:00
2026-09-125102026-09-12 00:00:00 to 2026-09-13 00:00:00
2026-09-131,3832026-09-13 00:00:00 to 2026-09-14 00:00:00
2026-09-143,7172026-09-14 00:00:00 to 2026-09-15 00:00:00
2026-09-155092026-09-15 00:00:00 to 2026-09-16 00:00:00
2026-09-165112026-09-16 00:00:00 to 2026-09-17 00:00:00
2026-09-178462026-09-17 00:00:00 to 2026-09-18 00:00:00
2026-09-184,5572026-09-18 00:00:00 to 2026-09-19 00:00:00
2026-09-19 (partial)1,8612026-09-19 00:00:00 to 2026-09-19 08:08:00
  • teas_citations: most recent retained observation before cutoff 2026-09-19 08:07:52.387 UTC; source query completed 2026-09-19 08:10:25 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 2026-09-19 08:07:43.000 UTC; source query completed 2026-09-19 08:10:28 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.
Keep reading

Where this leads next.

One study, one style, seven rooms. The legacy room addresses now land on the room that absorbed their content, and every machine mirror keeps its original path.

Tea notes and stock updates

Useful tea notes, only when there is something to say.

Stock arrivals, buying notes and practical guidance from the catalogue. No filler, no daily noise, unsubscribe in one click.

By family

By moment

Brand of the monthHyson Seasonal taster packsHow the seasonal bundles work Tea of the Month ClubCurator-picked monthly box Find your tea60-second quiz 0 Basket £0.00
See all 325 products