AWS Machine Learning Blog· Madhu Parthasarathy·· 3 d ago
Run agents securely and efficiently with the next generation AgentCore runtime
Run agents securely and efficiently with the next generation AgentCore runtime
AI summary
AI agents now run multi-step workloads for hours and act on behalf of users, raising the bar for secure, scalable agent compute. Learn how the next generation of Amazon Bedrock AgentCore runtime delivers hardware-isolated sessions with faster starts, more compute, usage-based billing, and isolation that now extends to your data.
Selection record
Threshold 60Official, first-handFirst 71Second 62
AdmittedSum of both 133 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：AgentCore运行时AI智能体部署技术更新
- Why it was chosen
- Gives the official multipliers for session start-up, compute ceiling and memory reclamation, so the cost and isolation trade-offs of the agent hosting layer can be judged.
- Same event
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