DXC OASIS采用Amazon Bedrock多模型架构
DXC Technology为关键IT运营构建了DXC OASIS,其底层采用Amazon Bedrock多模型治理机制,上层则负责编排、治理和保障。AWS称,Bedrock Guardrails可统一执行内容过滤、PII脱敏和禁用主题策略,PrivateLink可将推理流量保留在客户VPC内。DXC与AWS称,OASIS自2026年3月正式商用后,在56个实测用例中将平均解决时间缩短95%,但该数据来自厂商。
AWS Machine Learning Blog展示了一套将模型访问与运营控制分离的企业架构,并结合模型选择、私有网络和受限智能体权限服务受监管工作负载;性能数据仍由厂商提供。
This post is co-written with Nick Tamburro of DXC Technology.
When an AI agent can act on a production server at a bank or a hospital, access to a capable foundation model is only the starting point. Recent public incidents, in which autonomous agents took destructive actions their operators never intended, show that the real risk is rarely the model alone. It’s an agent holding more authority than its task requires, with nothing in the architecture to stop it. Avoiding that starts with a substrate that governs model access at the infrastructure level.
Amazon Bedrock provides that substrate. Through a single managed interface, it gives DXC OASIS access to multiple foundation models: Anthropic Claude, Amazon Nova, Meta Llama, and open-weight families. Amazon Bedrock Guardrails enforce content filtering, personally identifiable information (PII) redaction, and denied-topic policies uniformly across every model. AWS PrivateLink keeps inference traffic within the customer’s virtual private cloud (VPC), and serverless scaling avoids self-managed GPU infrastructure as a failure point. Because these are system-level controls rather than bolt-ons, they gave DXC Technology a governed foundation for what no model layer can deliver on its own: a trusted harness that orchestrates, governs, and audits AI agents across enterprise IT operations at scale.
#DXC OASIS#DXC Technology#Amazon Bedrock#Amazon Bedrock Guardrails#AWS PrivateLink#Anthropic Claude#Amazon Nova#Meta Llama#Amazon EKS#AWS KMS