You’ve tried an AI chatbot for troubleshooting, possibly for scripting. It helped—typically. However your Monday nonetheless begins the identical approach: manually constructing lab topologies, writing configurations from reminiscence, and documenting adjustments that no person reads till one thing breaks at 2 a.m.
The issue isn’t that AI doesn’t work. It’s that almost all community engineers are nonetheless on the primary two rungs of the aptitude ladder.
Three ranges of AI for community engineering
- Stage 1: Conversational AI. You ask an LLM to “generate a BGP EVPN configuration for my leaf switches,” and it offers a generic response—it doesn’t know your naming conventions, addressing scheme, or validated design patterns. Helpful for brainstorming, however the mannequin has no entry to your atmosphere.
- Stage 2: AI Assistants. The LLM positive factors entry to exterior sources—documentation through RAG, APIs, information. Cisco’s AI Assistant in Catalyst Middle—powered by the Deep Community Mannequin—is an efficient instance: it queries your community state and offers context-aware solutions. However for a multi-step workflow like constructing a lab topology, you’re nonetheless prompting one motion at a time.
- Stage 3: Agentic Frameworks. A single or multi-agent AI structure takes your necessities and orchestrates an entire multi-step workflow—utilizing instruments, area information, and your staff’s requirements—with you reviewing at vital steps. You outline the “what.” The agent handles the “how.”
The bounce from Stage 2 to Stage 3 will not be about smarter fashions. It’s a couple of totally different structure.
What makes an agentic framework
4 core parts make this work for community engineering:
- The AI agent is the reasoning engine—an LLM that interprets necessities, reads abilities, calls instruments, and decides the subsequent step. In superior setups, a number of brokers collaborate—a planning agent designs the topology whereas a validation agent checks the output.
- Expertise are markdown information that encode your staff’s area information—naming conventions, design patterns, templates. When a senior engineer leaves, their experience leaves with them. Expertise seize it in a format brokers devour immediately—runbooks the AI really follows.
- MCP (Mannequin Context Protocol) servers bridge brokers and your infrastructure APIs—Catalyst Middle, vManage, CML, ISE—to learn state, push configurations, or validate adjustments. As a result of MCP is an open commonplace, the identical servers work throughout any suitable framework.
- Human-in-the-loop gates are obligatory pause factors the place the agent waits to your approval. Nothing touches your infrastructure with out express sign-off. This isn’t a limitation—it’s the characteristic that makes enterprise adoption potential.
What this seems to be like in observe
Contemplate a typical job: constructing a BGP EVPN cloth lab in Cisco Modeling Labs for a buyer proof-of-concept.
- Handbook: 2-4 hours. Incomplete documentation. Information stays in a single engineer’s head.
- Agentic Framework: 10-Quarter-hour. Full documentation generated. Requirements utilized each time.
Engineer request to "Construct a BGP EVPN cloth — 2 spines, 2 leaves, OSPF underlay, iBGP overlay with VXLAN." Agent generates a plan — lab identify, 6 nodes, 8 hyperlinks, base configurations, boot order. Presents it for assessment.
Engineer critiques, adjusts the VXLAN VNI vary, approves. Agent executes through MCP — create_lab → add_node (×6) → add_link (×8) → set_node_config → start_lab. Agent verifies all nodes are lively, BGP EVPN neighbors established, VXLAN tunnels up. Generates documentation.
The agent isn’t producing textual content — it’s executing a workflow. It reads talent information to your requirements, calls MCP instruments to work together with the CML API, pauses to your approval, and produces reusable artifacts.
Constructing your first agentic workflow
You have got the framework—brokers, abilities, MCP servers, human gates. Now you want a workflow: a particular automated course of like constructing a lab or validating a design. Agentic frameworks like Claude Code, OpenCode, Windsurf, and Cursor all assist MCP and may orchestrate these workflows. The instance repository makes use of Claude Code to stroll via the complete sample:
- Outline abilities—Markdown information that seize your staff’s area information. The repo consists of ready-to-use abilities for EVPN cloth requirements, naming conventions, and IOS XE configuration templates. Begin with one workflow you repeat weekly and encode the choices you make each time.
- Join MCP servers—every server bridges an agent to a particular platform API. The repo features a CML MCP server you possibly can level at your lab occasion. CML is the best place to begin: low threat, excessive repetition.
- Configure brokers—outline what every agent does and the way they collaborate. The repo features a planning agent that generates topology designs and a validation agent that checks the output. You assessment and approve between steps.
- Create instructions—chain the workflow right into a single invocation: parse necessities → generate plan → human gate → execute → validate → doc.
When requirements change, you replace one talent file, not retrain an individual. Each agent interplay advantages from it.
Clone the repo, level the MCP server at your CML occasion, and run your first agent-assisted EVPN cloth construct in below half-hour.
The shift that issues
This isn’t about changing community engineers—it’s concerning the emergence of the AI-augmented community engineer. AI doesn’t simply pace up execution. It reshapes how engineers design, troubleshoot, doc, and protect information. Specialised brokers can plan topologies, validate configurations, or troubleshoot points in parallel—compressing hours of labor into minutes. Talent information codify years of tribal information that will in any other case stroll out the door when a senior engineer leaves. The engineer’s function shifts from job executor to orchestrator, curator, and decision-maker.
That shift calls for guardrails. LLMs hallucinate—they’ll generate plausible-looking configurations with incorrect subnet masks or nonexistent CLI instructions. Human-in-the-loop gates aren’t elective—they’re a core architectural requirement that retains the engineer in management as AI takes on extra of the workflow.
Cisco is already transferring on this route—Meraki’s Agentic Workflows, AgenticOps, and the Deep Community Mannequin all embed AI throughout community operations. The strategy described right here is complementary for engineers who want customized workflows or multi-platform orchestration.
The deeper affect is organizational. Agentic frameworks flip particular person experience into shared functionality. Design patterns develop into abilities. Validated designs develop into templates. Information that takes months of onboarding to switch turns into out there on day one—and improves with each interplay.
Begin small. Choose one workflow you repeat each week. Construct one talent file. Encode what you already know. Run your first agentic workflow construct. The shift from chatting with AI to working with an AI agent is smaller than you suppose—and the affect is bigger than you count on.
