Understand this story
CrossnoKaye built the AURA agent system based on Amazon Bedrock AgentCore, providing physical AI capabilities for its ATLAS software-defined automation platform, covering more than 100 industrial facilities and 13,000 controlled devices. AURA runs Python computations in isolated microVM sandboxes via AgentCore's code interpreter to compensate for the LLM's shortcoming in reliably handling massive volumes of sensor numerical data. CrossnoKaye says its APC application increased production throughput by 11–17% and reduced total facility energy consumption by an average of 21%. There are currently no subsequent developments.
AI-generated from public reports
Latest development · Report
How CrossnoKaye Uses Amazon Bedrock AgentCore to Provide Grounding Support for Physical AIDevelopments
1 confirmed developments
- Source:AWS Machine Learning
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 10
AWS Machine LearningFirst-party
How CrossnoKaye Uses Amazon Bedrock AgentCore to Provide Grounding Support for Physical AI
CrossnoKaye built the AURA agent system on Amazon Bedrock AgentCore to provide physical AI capabilities for its ATLAS software-defined automation platform, covering more than 100 industrial facilities and 13,000 controlled devices. AURA uses AgentCore's code interpreter to run Python computations in isolated micro-VM sandboxes, compensating for the LLM's inability to reliably handle massive volumes of sensor values. CrossnoKaye says its APC application increases production throughput by 11–17% and reduces total facility energy consumption by an average of 21%.