Two Clocks of Recruitment in AI Engine Pipelines: Serving-Time Retrieval, Knowledge Graph Updates, and LLM Assimilation

Existing discussions of AI search often treat content selection as a single retrieval event. This paper argues that AI engine pipelines operate on two recruitment clocks. The first is serving-time recruitment: search and retrieval systems select content from serving-available pools in response to live queries, with effects visible through citations, rankings, answer inclusion, and query-fanout analysis. The second is update-cycle assimilation: Knowledge Graph update cycles and Large Language Model training pipelines incorporate selected evidence into durable internal states through slower refresh, curation, training, and deployment cycles, with effects observable only indirectly through structural drift, stable answer language, and reproduction of a frame across systems and releases. The distinction resolves to an axiom: citation is evidence of serving-time recruitment, not of durable assimilation; assimilation can occur without citation, and citation can occur without assimilation. Fast-clock visibility without slow-clock assimilation is borrowed visibility. The paper formalises the two-clock model, treats the web index as a shared evidential substrate rather than a literal architectural layer, maps recruitment behaviour across the Algorithmic Trinity, and identifies implications for measurement, optimisation, and temporal opacity. Five testable predictions are advanced. This is a practitioner-led conceptual working paper, not an empirical study.

This paper is TKF-12-20647182 in The Kalicube Framework series by Jason Barnard (Kalicube). Canonical citation identifiers for the whole research programme are maintained in The Kalicube Framework Programme Register (TKF-0): https://doi.org/10.5281/zenodo.20645889. Cite this paper as TKF-12-20647182 (Zenodo concept DOI 10.5281/zenodo.20647182).

AI usage disclosure: in the preparation of this paper, the author used Claude (Anthropic) for drafting, structured thinking, and editorial preparation, and Perplexity for literature search, reference verification, and critical review of drafts. All conceptual content, theoretical claims, and intellectual contributions are the author's own. The author reviewed, revised, and approved all text and takes full responsibility for the content of this publication.