Natural language security queries at Orca Security using Amazon Bedrock
Orca Security built Discovery AI, a natural language query agent on Amazon Bedrock that converts plain-English questions into Sonar queries. The post shares the multi-stage architecture and the results: 90% lower query cost, 93% fewer input tokens, and 75% lower latency than the initial baseline.
Security analysts often struggle to quickly access cloud infrastructure data without extensive knowledge of specialized query languages. To address this, Orca Security partnered with AWS to develop Discovery AI, a natural language query agent on Amazon Bedrock. This system converts natural language questions into structured Sonar queries for fast, secure cloud analysis.
By implementing a nine-stage pipeline on Amazon Bedrock, Orca achieved a 90% reduction in query costs, 93% decrease in input tokens, and 75% improvement in latency compared to their original system.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
