Relevance
This is what agentic retrieval looks like
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.
Blog
Proof
What we learned building a 100M-document search engine, part 3: Hybrid search depends on query type
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.
Proof
What we learned building a 100M-document search engine, part 2: ANN Tuning
We expected ANN tuning to be straightforward. It was not. Embedding bias, graph connectivity, and quantization loss interacted in ways that only surfaced at 100 million documents.
Relevance
Deep research is a retrieval problem
Give the agent the relevant documents and it answers 93% of questions correctly. Make it find those documents with a weak retriever and it scores 14%. In BrowseComp-Plus, that gap makes retrieval impossible to ignore.
Proof
What we learned building a 100M-document search engine
We built a retrieval system over 100 million web documents. The biggest lesson was not about any single configuration. When every experiment takes 30 hours, the speed of your reindex-evaluate loop determines how good your system can get.
Thinking traces
The context window is not your database
Context windows can hold more than ever, but more context doesn't mean better answers. Here's why retrieval still matters, especially for agents.
