{"version":1,"type":"story","url":"https://digestai.news/story/orca-security-cuts-cloud-query-costs-by-90-with-amazon-bedrock-agent","json":"https://digestai.news/story/orca-security-cuts-cloud-query-costs-by-90-with-amazon-bedrock-agent.json","markdown":"https://digestai.news/story/orca-security-cuts-cloud-query-costs-by-90-with-amazon-bedrock-agent.md","slug":"orca-security-cuts-cloud-query-costs-by-90-with-amazon-bedrock-agent","headline":"Orca Security cuts cloud query costs by 90% with Amazon Bedrock agent","summary":"Orca Security partnered with AWS to build **Discovery AI**, a natural language query agent on **Amazon Bedrock** that converts plain-text security questions into structured cloud queries. The tool reduces query costs by **90%**, input tokens by **93%**, and latency by **75%** compared to its initial baseline, handling thousands of daily requests since March 2026.\n\nThe system uses a **nine-stage pipeline** with specialized models—including **Anthropic Claude Haiku 4.5** for reasoning and **Amazon Titan** for embeddings—to parse user requests, filter irrelevant models, and validate outputs. A **human-in-the-loop labeling system** continuously improves accuracy by letting domain experts correct misclassified queries. Orca’s **Sonar** platform supports **900+ cloud models**, but the agent dynamically narrows context to only relevant schemas, avoiding the inefficiency of loading all definitions at once.","keyPoints":["Discovery AI slashes query costs by **90%** and input tokens by **93%** using Amazon Bedrock’s multi-model pipeline","Latency drops from **60 seconds to 15 seconds** per request via staged model allocation and RAG-based retrieval","Human labeling system lets Orca experts refine examples in real time, improving accuracy for evolving cloud environments"],"whyItMatters":"This demonstrates how AI agents can bridge complex query languages with natural language, cutting operational costs for security teams while scaling to production workloads. The approach may inspire similar optimizations for other structured-data domains like finance or logistics.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Orca Security","Amazon Web Services","AWS","Anthropic","Cohere"],"models":["Amazon Bedrock","Anthropic Claude Haiku 4.5","Amazon Nova 2 Lite","Amazon Titan","Cohere Rerank 3.5"],"people":["Or Gabay"]},"firstPublishedAt":"2026-10-13T16:03:31Z","updatedAt":"2026-10-13T16:03:31Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"AWS Machine Learning Blog","title":"Natural language security queries at Orca Security using Amazon Bedrock","url":"https://aws.amazon.com/blogs/machine-learning/natural-language-security-queries-at-orca-security-using-amazon-bedrock","publishedAt":"2026-10-13T16:03:31Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Amazon Bedrock Becomes Enterprise AI Operating System","url":"https://digestai.news/thread/amazon-expands-seller-assistant-from-chatbot-to-operating-system-for-merchants","storyCount":10},"cite":{"text":"Digest AI, \"Orca Security cuts cloud query costs by 90% with Amazon Bedrock agent\", 13 October 2026, https://digestai.news/story/orca-security-cuts-cloud-query-costs-by-90-with-amazon-bedrock-agent","publisher":"Digest AI","title":"Orca Security cuts cloud query costs by 90% with Amazon Bedrock agent","datePublished":"2026-10-13T16:03:31Z","url":"https://digestai.news/story/orca-security-cuts-cloud-query-costs-by-90-with-amazon-bedrock-agent"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}