Architecture Shift
Impact: Important
Strength: High
Conf: 85%
Cisco Details How AI Agentic Frameworks Reshape Network Operations Architecture
Summary
Cisco's blog details the application of AI Agentic frameworks in network engineering, outlining an evolution from chatbots to multi-step workflow orchestration. The core involves encoding human expertise into 'skill' files, connecting to infrastructure APIs via the MCP protocol, and setting human-in-the-loop gates, shifting the engineer's role from task executor to orchestrator.
Key Takeaways
Cisco categorizes network AI capabilities into three levels: Conversational AI, AI Assistants, and Agentic Frameworks. The latter's core consists of four components: AI agents, skill files, MCP servers, and human-in-the-loop gates.
The framework uses the open-standard Model Context Protocol (MCP) to connect AI agents to platform APIs like Catalyst Center and CML, enabling state reading and configuration pushes. Skill files codify team design patterns and naming conventions into Markdown, transforming individual knowledge into reusable organizational assets.
Using the example of automating a BGP EVPN lab build in CML, the blog demonstrates how the framework compresses hours of manual work into 10-15 minutes, generates full documentation, and ensures standards compliance with each execution.
The framework uses the open-standard Model Context Protocol (MCP) to connect AI agents to platform APIs like Catalyst Center and CML, enabling state reading and configuration pushes. Skill files codify team design patterns and naming conventions into Markdown, transforming individual knowledge into reusable organizational assets.
Using the example of automating a BGP EVPN lab build in CML, the blog demonstrates how the framework compresses hours of manual work into 10-15 minutes, generates full documentation, and ensures standards compliance with each execution.
Why It Matters
This signals a shift in network operations from tool-assisted tasks to an AI agent-driven 'orchestration layer.' The control point moves from engineers' manual CLI operations to the definition and management of skill libraries, workflows, and approval rules. Cisco is advancing on two fronts—open frameworks (MCP) and internal products (Deep Network Model)—to establish its core platform position in this new architecture....
PRO Decision
Decision recommendations are available for Pro users
Upgrade to Pro $29/mo