The post gives concrete step, token, and accuracy figures for an agent search tool, helping readers judge whether file retrieval is worth changing in their own agent workflows.
Impressive work on decision models for agentic search.
Drex Search looks like a big upgrade for agents working over large file collections. It decides where to look, reads only the pages that matter, and stops when it can cite the source.
This is a great fit for Claude Code, Codex, and Hermes Agent, where poor retrieval often leads to wrong answers.
Nace reports 62% fewer agent steps and 56% fewer tokens per question, with +4 points of accuracy on average.
Introducing Drex for Search 🔍 Supercharge your agentic search with Decision-powered retrieval Standard file search holds AI agents back. Drex changes that: • 62% fewer steps to find answers • 56% tokens saved • +4% performance boost across Claude Code, Codex, OpenCode, Hermes, and PI Validated across 6 professional work benchmarks like OfficeQA (529 real-world queries) Upgrade your agentic workflows with the File Search API Try for free: https://console.nace.ai Faster agents. Cheaper runs. Sharper accuracy.
elvis · x.comPublished
Original title: Impressive work on decision models for agentic search.
