Natural language security queries at Orca Security using Amazon Bedrock
AWS Machine Learningen

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.
This is a short summary published by AI Global Wire. The full article is owned and hosted by AWS Machine Learning — open it there to read it in full.
Read the full story at AWS Machine Learning- Agenter
Related AI news
- Run fast, private agents on-device with LFM2.5-24B-A2BHugging Face · October 13, 2026
- How ShipStation Global built an AI IT help desk on Amazon Bedrock AgentCoreAWS Machine Learning · October 13, 2026
- Build long-horizon agents with Grok 4.7 on Amazon BedrockAWS Machine Learning · October 13, 2026
- Workday makes Sana its new home for AI-driven HR and financeSiliconANGLE · October 13, 2026
- Scuba, which is building a "context engine" designed to serve as a shared memory hub for human workers and AI agents, raised $34M across pre-seed and seed (Alex Konrad/Upstarts Media)Techmeme · October 13, 2026
- AI services may account for almost half of Infosys' work in 2-3 years: CEO Salil ParekhEconomic Times Tech · October 13, 2026