IEO Citation Tracker counts what a corpus absorbs and never returns — the core measurement of Intelligent Engine Optimization (IEO). Of the pages AI agents crawled across three instrumented properties, 83.7% to 97.2% were never retrieved into an answer — read repeatedly, used never. 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 →
The context length and retrieval scope within which an AI inference engine operates for a specific query. The inference window determines how many sources can be considered, how much content from each source can be examined, and how the resulting synthesis is constructed.
Different AI platforms have different inference window characteristics. Some retrieve and consider many short sources; others retrieve fewer but examine each more deeply. Understanding the inference window pattern of each target platform informs content design decisions about page length, section structure, and information density.
The IEO Engine methodology produces content that performs well across the range of inference windows employed by major AI platforms — long enough to provide substantive material for deep-examination platforms, structured enough for short-extraction platforms to find clear citable units.