Orca Security Launches Discovery AI on Amazon Bedrock to Slash Query Costs
Current overview (not historical)
Orca Security has partnered with AWS to build Discovery AI, a natural‑language query agent running on Amazon Bedrock. The system translates user queries into Sonar queries, cutting query cost by 90%, input token usage by 93%, and latency by 75%. Since March 2026, Discovery AI has processed thousands of queries daily in production, demonstrating a significant efficiency boost for security operations.
Written with AI from the reporting · updated 10/14/2026
Expand the detailed fact route and sources
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Unclassified fact stationOct 14, 00:00recorded Oct 14, 22:23single source
Orca Security builds Discovery AI on Amazon Bedrock
Read original source ↗ AWS Machine Learning BlogReplay this moment in the explorerEvidence & revisions · 1 source records
- Subject:
- Orca Security
- Action:
- built Discovery AI on Amazon Bedrock
- Object:
- natural language query agent for Sonar query system
- Occurred (fact side):
- Oct 14, 00:00
- Published (valid side):
- Oct 14, 00:03
- First seen (known side):
- Oct 14, 22:23
Fact stationSingle source · one-sided claimCopy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.
Uncertainty marks flag where to check the sources; they are not proven causation.
Report timeline
Explore every side through dated source reports.
- AWS Machine Learning BlogFirst-party sourceRelated fact: single sourceOrca Security builds Discovery AI on Amazon Bedrock for natural language security queries
Report first recorded Oct 14, 22:23
Orca Security partnered with AWS to develop Discovery AI, a natural language query agent on Amazon Bedrock, which converts plain text questions into valid Sonar queries across over 900 cloud models. This solution reduced query costs by 90 percent, input tokens by 93 percent, and latency by 75 percent compared to the initial baseline, enabling security analysts to query complex cloud infrastructure without deep familiarity with domain-specific query languages.
Read original source ↗
Event discussion
Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.