Blog

Bots became the majority of the web traffic Cloudflare measures, ahead of forecast. Projections for agent query volume run to 1000x. Here is what the data actually supports.

Same retriever and model, different harness: 65% higher recall, 51% fewer prompt tokens, 44% lower cost.

Frontier models are strong at code, and code lets agents manage retrieval without filling context. The next step is programmable retrieval primitives, not just programmable query loops.

A human types two words; an agent sends ten. That shift in query mix means 8.4x the cost to serve.

GPT-5 searches like a power user. Phrase quotes in 98% of sessions. Median query length past the human 99th percentile (AOL query log). The new user of search.

Hybrid search does not have one best weight. Agentic, all-words-included, and human-style queries each stress retrieval differently, which means evaluation has to be stratified.