How AI Platforms Search Fan-Out Query Behavior Across Intent Types, Verticals, and Platforms

Abstract

When users submit queries to AI search platforms, the platforms do not pass the user's text to web search verbatim. They decompose each prompt into multiple internal "fan-out queries" — the actual strings sent to retrieval engines. These fan-out queries determine which pages get fetched, which enter the AI's context window, and which get cited in the response. Despite their centrality to AI search discoverability, fan-out queries have not been studied at scale. This study classifies 1,323 fan-out queries generated by 540 parent queries across three AI platforms (ChatGPT, Gemini, Perplexity), ten commercial verticals, and five intent types. We capture fan-out queries via the OpenAI Responses API, Google GenAI grounding metadata, and Perplexity browser-level SSE interception. Nine findings emerge. First, user intent is a significant predictor of fan-out composition (X2=299.6, p<0.001, V=0.24): discovery queries trigger 3.3x the entity injection rate of informational queries. Second, platforms exhibit distinct retrieval personalities — ChatGPT injects entities from training data on 32% of fan-outs, Gemini casts a wide net with 27% expansion queries, and Perplexity leads in evidence-seeking at 21%. Third, ChatGPT's search trigger rate varies dramatically by model tier: gpt-5.4 searches on only 29% of queries while gpt-5.4-nano searches on 100%, suggesting larger models are more confident in answering from training data alone. Fourth, platform-intent interaction effects explain fan-out variation better than either factor alone (two-way AIC=192 vs main-effects AIC=937). Fifth, situation-first query phrasing produces significantly different fan-out distributions than standard phrasing (V=0.35, p<0.001). Sixth, no significant vertical effect was detected at this sample size (H=6.26, p=0.71, 18 queries per vertical), suggesting intent and platform are the dominant factors. Seventh, replicate analysis on ChatGPT (gpt-5.4-mini, 3 replicates) reveals that the search trigger decision is highly deterministic (91.7% agreement) while the specific fan-out query strings are almost entirely stochastic (98% zero overlap) — but the structural *type* of fan-out is moderately stable (65% top-type agreement). These findings establish that AI search operates a two-layer retrieval system: a model-confidence layer that decides whether to search at all, and a query-decomposition layer that determines what to search for. Optimising for AI citation requires understanding both layers

Keywords