FULL STORY
Nace AI's Drex for Search: From Launch to Top of MADQA
Nace AI launched Drex for Search, a decision-powered retrieval product for agents, on October 26. Two days later it topped Snowflake's MADQA leaderboard, answering 94.7% of 500 enterprise document QA questions correctly.
2026-10-26 ~ 2026-10-28 · 2 episodes · 5 posts
Episode 1 · Nace AI Launches Drex for Search to Cut Agent Retrieval Costs (2026-10-26, 3 posts)
Nace AI launched Drex for Search, offering page-level precise retrieval of cloud documents for AI agents. Official tests show it saves about 397K tokens per query, cuts latency by 56.8%, and reduces retrieval steps by 62%.
- Nace AI launches Drex for Search, cutting agent steps 62% and tokens 56% — testingcatalog · 2026-10-26
- Drex for Search hits Nace API console, saving 397k tokens and 56.8% latency per query — testingcatalog · 2026-10-26
- Drex Search cuts agent steps 62% and tokens 56% with decision-powered retrieval — _AustinCalvert_ · 2026-10-27
Episode 2 · Nace AI's Drex for Search Tops Snowflake MADQA Leaderboard (2026-10-28, 2 posts)
Nace AI's Drex for Search ranked first on Snowflake's MADQA leaderboard, answering 94.7% of 500 enterprise document QA questions correctly. It can be plugged into Claude via MCP and reportedly cuts coding agent steps by 62%.
- Drex for Search tops Snowflake MADQA leaderboard with 94.7% on 500 doc questions — testingcatalog · 2026-10-28
- Nace AI's Drex for Search Tops Snowflake MADQA With 94.7% Accuracy — testingcatalog · 2026-10-28