思科为9万员工部署个性化AI代理，接入800多个子代理
Cisco gave 90,000 employees personalized AI agents backed by more than 800 subag…
Cisco gave 90,000 employees personalized AI agents backed by more than 800 subagents.
思科为9万名员工提供了个性化AI代理，这些代理由超过800个子代理支持。
For cost control, 50%-60% of requests go to open-weight models, 20%-30% to software automation, and only a small remainder goes out to a frontier model.
为了控制成本，50%-60%的请求由开放权重模型处理，20%-30%由软件自动化处理，只有一小部分剩余请求发送给前沿模型。
The agent, called MyAgent, sits on infrastructure Cisco has built since 2023, when its internal assistant initially ran on Azure OpenAI.
这个名为MyAgent的代理，建立在思科自2023年以来构建的基础设施之上，当时其内部助手最初运行在Azure OpenAI上。
Now each agent pulls employee-specific context through permissioned enterprise connectors and can call more than 800 backend subagents.
现在，每个代理通过权限化的企业连接器获取员工特定上下文，并能调用超过800个后端子代理。
Those subagents can track sales-forecast variances or send anomaly notifications, while the personal agents remain isolated from other employees' agents.
这些子代理可以跟踪销售预测差异或发送异常通知，而个人代理则与其他员工的代理保持隔离。
External actions still require explicit human approval, and a policy server can block destructive operations or prevent Cisco data from training third-party models.
外部操作仍需明确的人工审批，策略服务器可以阻止破坏性操作或防止思科数据训练第三方模型。
Cisco had already built multi-model routing across Azure OpenAI, Claude, Gemini and its own Deep Network Model, so MyAgent extends an existing orchestration layer.
思科已经在Azure OpenAI、Claude、Gemini及其自己的深度网络模型之间建立了多模型路由，因此MyAgent扩展了现有的编排层。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力