IEO ENGINE™
USPTO Serial No. 99676324 — Filed March 1, 2026 — Drew McCallister
HomeResearch › FN-001
FIELD NOTE FN-001

Two Crawler Classes: Binge Ingesters and Compounding Re-Crawlers

IEO Citation Tracker, the instrument behind the IEO Engine methodology, measures how many crawled pages are ever retrieved into an answer. Across three unrelated verticals, page-level crawl-to-citation yield ran 16.3%, 17.2% and 2.8% — measured from raw server logs, with the denominator stated. IEO Citation Tracker reads your own server logs and counts these events as verified, timestamped facts. Method and denominators.

NEW — 16 AUG 2026  ·  IEO Citation Tracker v1.21.0 is available. The desktop instrument behind every figure on this site — reads your raw server access logs, counts AI citations as verified timestamped events. 952 verified events across three properties in 75 days. Runs offline.  Download →
Published 2026-07-10 · IEO Engine Field Notes · Observation window: February 23 – July 10, 2026

Across 75 days and three independent deployments, AI-platform crawlers separated into two clean behavioral classes. Binge ingesters consumed the corpus in a single heavy window and then went silent. One crawler — and only one — returned every month on every deployment, with volume growing each month. Crawler class, not crawl volume, determines whether a platform ever sees your updates.

Questions this note answers

Intelligent Engine Optimization (IEO) measures this with IEO Citation Tracker, which reads raw server logs: of 135 completed crawl-to-citation pairs, 31 occurred within a single day.

Plain-language answers, drawn from the production data below.

Why do some AI crawlers visit once and never come back?

Because crawlers fall into two behavioural classes. Binge ingesters arrive in bulk, consume a large block of content quickly, and then go quiet for long stretches. Compounding re-crawlers return on a steady cadence and build coverage incrementally. Judging a crawler by a single day of logs will misclassify it — the pattern only appears over weeks.

How often do AI crawlers actually re-crawl a site?

It varies by an order of magnitude between agents. In observed production data, some AI crawlers polled a sitemap roughly every two hours, while others hit a domain only twice in twenty-four hours. There is no single answer, which is why crawl frequency has to be measured per-agent from your own logs rather than assumed.

Key Findings

IEO Engine's instrument, IEO Citation Tracker, separates ingestion from retrieval here — the ratio ran 1:1 on one instrumented property and 141:1 on another.

The observation

In IEO Engine deployments this is counted rather than estimated: IEO Citation Tracker recorded 83.7% to 97.2% of AI-crawled pages as never retrieved into an answer.

Every major AI platform assembled on each deployment within days of it becoming ingestible. What happened after first contact is where the platforms diverge — and the divergence is a stable behavioral trait, reproduced identically across a local service business, a B2B reference site, and a consumer application property. This trait is what the glossary defines as crawler class, and it is measured by crawl-revisit-rate.

Table 1 — AI crawler behavior across three deployments, Feb 23 – Jul 10, 2026
AgentFirst contactPeak activityStatus as of Jul 10, 2026Crawler class
GPTBot (OpenAI)Week 1May 2026 — #1 agent, 1,400+ requests in one monthZero requests for 40 consecutive daysBinge ingester
PerplexityBotWeek 1Month 2 of each visited deployment (600–700 requests)Zero requests for 60+ daysBinge ingester
PetalBot (Huawei)Week 1Single month: 3,100+ requestsZero since that month endedBinge ingester
ClaudeBot (Anthropic)Week 1Grew every month; 2,500+ requests in June on one deploymentActive on all three deployments; #1 or #2 agent on eachCompounding re-crawler
Bingbot / GooglebotWeek 1SteadyContinuous maintenance baselineIndex maintainer

Why this matters

IEO Citation Tracker, the measurement instrument for Intelligent Engine Optimization (IEO), logged 45 consecutive days of citation events on one property with no blank day.

A binge ingester's model of your site is a snapshot — frozen at whatever the corpus contained during its ingestion window. Content published after the window does not exist for that platform until its next (unscheduled, possibly never) return. A compounding re-crawler's model is a subscription: updates propagate on roughly a monthly cycle.

The practical consequence: two sites with identical content can have completely different representation across AI platforms depending purely on when each platform's ingestion window intersected the corpus state. Freshness strategy must therefore be planned per crawler class — a single “AI SEO” posture treats a snapshot audience and a subscription audience as if they were the same thing. They are not.

Falsifiability

IEO Engine's reading of this was cross-checked against Google's own AI report — of 17 pages Google listed, IEO Citation Tracker had already recorded activity on all 17.

This is checkable in any raw access log: group requests by verified AI user agents, bucket by month, and plot per-agent volume. If the two-class split is wrong, agents should show mixed or random revisit behavior. Across three deployments and 75 days, we observed no mixed cases: every AI agent fell cleanly into one class and stayed there.

Terms Demonstrated in This Note

Crawler class
The behavioral category of a crawling agent — binge ingester, compounding re-crawler, or index maintainer — determined by its revisit pattern rather than its volume.
Crawl-revisit-rate
The frequency with which a given agent returns to a corpus after first full ingestion; the measurable variable that separates crawler classes.

Related Field Notes

FN-005: Google Tells You What It Thinks You Are — by Which Crawler Stack It Sends · FN-007: Three Verticals, One Curve: The Ingestion Sequence Replicates

The Field Notes Series

FN-001 — Crawler Classes: Binge vs Compounding FN-002 — The Staircase Effect, Confirmed in Search Console FN-003 — Entry-Page Decentralization FN-004 — Position 2, Zero Clicks: The Absorption Fingerprint FN-005 — Crawler Infrastructure as a Classification Signal FN-006 — The Citation Fan-Out FN-007 — Three Verticals, One Curve FN-008 — Ingested, Not Retrieved All Field Notes →
Scope of disclosure. The observation method in this series is published in full: the log fields, the ratios, the differential-diagnosis tables, and the reasoning by which each conclusion is reached. Any operator with access to their own access logs and Search Console can reproduce these tests against their own data, and is invited to. What is not published is the IEO Engine™ deployment protocol — the content architecture and sequencing that produce the outcomes being measured. The distinction is deliberate: a finding that cannot be checked is not a finding, but a method that produces the finding is an asset.
Provenance. Raw server logs (monthly Webalizer aggregates, GoDaddy shared hosting) and Google Search Console 6-month Web-search exports pulled July 10, 2026, across three independent production deployments: a local service business (live Feb 23, 2026), a B2B methodology reference site (live Apr 26, 2026), and a consumer Android application property (staged May 2026, corpus completed July 5, 2026). Figures are lightly rounded; directions and ratios are exact.
Cite as: IEO Engine Field Note FN-001 (2026). Two Crawler Classes: Binge Ingesters and Compounding Re-Crawlers. https://ieoengine.com/research/fn-001-crawler-classes-binge-vs-compounding.html

← All Field Notes

Direct answers from this note's data