AWS Machine Learning Blog· Raphael Simon·· 6 d ago
How CrossnoKaye grounds physical AI with Amazon Bedrock AgentCore
How CrossnoKaye grounds physical AI with Amazon Bedrock AgentCore
AI summary
CrossnoKaye brought physical AI to heavy industry with Amazon Bedrock AgentCore. Its ATLAS platform and AURA agentic system ground AI reasoning in live plant data and run verifiable Python in isolated AgentCore sandboxes, giving plant engineers checkable, math-backed answers instead of model guesses.
Selection record
Threshold 60Official, first-handFirst 34Second 42
Not admittedSum of both 76 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：正文详述AURA智能体与Bedrock AgentCore架构
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: AWS Machine Learning Blog · aws.amazon.com