Drex Search cuts agent steps 62% and tokens 56% with decision-powered retrieval
_AustinCalvert_ · x · 2026-10-27
Nace launched Drex for Search, a decision-powered retrieval layer for AI agents working over large file collections.
- Validated on 6 professional benchmarks including OfficeQA (529 real-world queries): 62% fewer steps, 56% fewer tokens, +4 points accuracy on average
- Fits Claude Code, Codex, OpenCode, Hermes and PI, where poor retrieval often causes wrong answers; the agent decides where to look, reads only relevant pages, and stops once it can cite a source
- Available via a File Search API with a free tier
Related event: Nace AI Launches Drex for Search to Cut Agent Retrieval Costs(3 posts)→
More from coding & agent
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27
- AI agents may soon become the only way to run code, not just write it — IgorCarron · 2026-10-27
- Hermes Agent used as browser QA tester finds 8 issues in a bug-seeded site — techlatest_net · 2026-10-27
- Open-source FableCut lets AI agents edit a real video timeline via remote MCP — FastPresence9799 · 2026-10-27