“The shift for builders is extra radical than we expect.”
— Jeetu Patel, President and CPO, Cisco
AI is working full throttle, leaving a wake of radical adjustments for software program builders. We’re coming into a time the place AI can write code, name instruments, and execute advanced workflows—all from a single immediate. This shift has large implications. Learn Jeetu’s weblog to be taught extra.
Radical shifts are on the horizon for extra than simply builders.
What about AI’s affect on community engineers?
In my earlier weblogI described MCP—Mannequin Context Protocol—and the way agentic AI might lastly communicate our language, perceive our networks, and take significant motion. Now I need to present you what occurs when that dialog goes one step additional: when the agent doesn’t simply perceive what’s damaged however fixes it with out being informed how.
From detection to motion: a self-healing community
A self-healing community isn’t a hypothetical “what-if.” That is agentic AI dealing with one of the irritating points in community operations: configuration drift.
Let’s break down the method of creating self-healing occur.
On this setup, I deployed two MCP servers—one integrates with my occasion of Splunk Enterprise, and the opposite integrates with my Meraki dashboard. What makes this particular isn’t simply the instrument integration—it’s that the agent could make autonomous selections throughout each instruments based mostly on a easy immediate.
Server 1: Splunk MCP
On the Splunk MCP server, we begin with a pure language immediate like this:
- “What are my Splunk Indexes?”
- “Search the meraki_index for any system connectivity points or standing adjustments within the final 4 hours.”
- “Present me all community configuration adjustments and group them by the one that made them.“
- “Analyze community visitors patterns and determine any anomalies that would point out safety threats.“
The agent processes the request—beneath the hood— like this:
The Splunk MCP server makes use of the Splunk SDK to question actual log information. Its job is to detect if one thing within the setting—like a configuration change—has occurred from what we anticipate, evaluate it to our supply of reality, and treatment it.
Let’s attempt self-healing with an agent we’ll name “Community Pharaoh.”
Right here’s immediate to start out:
Immediate > I have to see what’s taking place with my Meraki community. Are you able to present me the most recent Splunk alerts, particularly within the Merraki_index? I want you to look within the spath the place the supply is Meraki Community solely throughout the previous 3 weeks.
You’ll discover that I didn’t have to be particular about easy methods to search. I simply wanted to inform the agent what I used to be after.
Spectacular, proper? Right here’s what Community Pharaoh did:
- Preliminary search try – Tried looking out meraki_index with supply= “Meraki Community” however received a syntax error.
- Question format repair – Adjusted Splunk search syntax to correct format.
- Broad reconnaissance – Searched the complete Meraki Index to know the information construction and obtainable sources.
- Information evaluation – Discovered two most important sources: “Residence Community” (port occasions) and “Meraki Community” (config adjustments).
- Focused extraction – Centered particularly on “Meraki Community” supply as requested.
- Alert parsing – Extracted key fields: alert sorts, ranges, gadgets, and alter particulars from JSON payload.
This was all by itself, together with the self-correction and retries to get the end result I requested.
Server 2: Meraki MCP
The second MCP server is the place the “self-healing comes into play.”
After the Meraki MCP server receives the detected change (for instance, system IP tackle change), it makes use of the Meraki dashboard API to reverse that change. No handbook directions, no pre-programmed response chain. The agent understood that the change represented drift and took motion to revive alignment.
Key takeaways
- I didn’t have to jot down a hardcoded if-then circulation between the 2. I simply outlined the instruments and gave the agent context. The agent selected the suitable instrument, chosen the right perform, and acted fully autonomously.
- I outlined the instruments decorators to make obtainable in my Meraki MCP–nothing earth-shattering–easy features that execute one factor and one factor solely—get a listing of my gadgets, replace my gadgets, and so forth— all of which community engineers have possible used and coded.
That is what occurs if you let intent drive the motion and let the agent do the orchestration. It’s easy, scalable, and highly effective.
Now, let’s have a look at how the agent self-heals our community with Meraki MCP (that features precise output).
First, we’ll get a diff of what was modified.
Immediate > This Kareem Iskander dude shouldn’t have made any adjustments to the community. Unacceptable! Are you able to present me side-by-side what was modified?
As soon as once more, spectacular! Discover that the knowledge is being pulled from Splunk by the Splunk MCP server. Additionally, discover how our agent gave us ideas on easy methods to revert the adjustments. As soon as once more, spectacular! Discover that the knowledge is being pulled from Splunk utilizing the Splunk MCP server.
Additionally, I’d wish to level out how our agent gave us ideas on easy methods to revert the adjustments routinely utilizing the obtainable API endpoints within the Meraki MCP! I didn’t should specify which Meraki group or community the gadgets belong to, nor did I’ve to specify the system sort. Community Pharaoh knew the hierarchy of the Meraki dashboard and traversed it!
Now, it’s time to heal the community!
Immediate > NetP Let’s revert the configuration to its unique state for all of the adjustments you’ve gotten detected!
Why this issues
This isn’t only a enjoyable facet mission. It addresses an actual ache level for all community engineers: configuration drift!
Whether or not it’s unintentional adjustments, unauthorized edits, or misalignment with the supply of reality, config drift results in downtime, compliance points, and countless handbook cleanup. Agentic AI presents a greater mannequin: detect, perceive, and repair routinely.
I simply took two steps and let the agent run with it:
- Outline the instrument interfaces (Splunk SDK + Meraki API)
- Register these instruments with MCP
That is the ability of constructing agentic techniques on prime of the workflows we already know.
What expertise do you really want?
Let’s preserve it actual. Listed below are the talents required:
- Coding with Python
- Understanding SDKs and easy methods to use them
- Community automation and programmability with APIs
- MCP framework to construction instrument entry and execution
- Networking expertise
The place that is all going
Let’s zoom out for a second to raised perceive the massive image.
What I’ve constructed right here—a self-healing community utilizing two MCP brokers—isn’t a prototype. It’s a sensible preview of Cisco’s broader imaginative and prescient.
Within the AI Canvas announcementCisco laid the inspiration for the agentic period: modular brokers that work with our instruments, perceive our intent, and take autonomous motion. This demo matches proper in. One agent detects drift by Splunk, one other acts by Meraki—all with only a immediate and some registered instrument features.
Now think about layering in Cisco’s Deep Community Mannequin—a complete, machine-readable understanding of your whole community, skilled on years of CCIE-level Cisco experience and telemetry, and a set of pre-built brokers prepared out of the field.
As a substitute of merely reversing a misconfigured VLAN, the agent understands:
- Which purposes rely upon that VLAN throughout hybrid environments
- Whether or not the change launched a segmentation violation or efficiency regression
- The best way to resolve the difficulty with out disrupting crucial enterprise visitors
- The best way to replace the supply of reality to replicate any official intent behind the change
That is the place the speculation turns into a actuality:
- You’ve gotten Canvas provides us the setting and brokers.
- The Cisco Deep Community Mannequin provides brokers the situational intelligence to behave with context.
- MCP provides us the extendibility to BYOA (deliver/construct your personal agent, which is a future function).
And that’s what community engineers want—not one other platform, however an assistant that will get it; one that may motive like us, function quicker than us, and make selections we belief.
It’s time to sit down within the driver’s seat
This isn’t a one-off. It’s a multiplier. Collectively, AI Canvas, Cisco Deep Community Mannequin, and MCP put community engineers within the driver’s seat of this new agentic AI period. As Jeetu additionally mentioned, “The long run is coming quicker than you assume.”
Keep forward of the curve and be a part of the extraordinary.
For a totally working code of this demo, take a look at my GitHub repository.
Unlock the way forward for know-how with synthetic intelligence coaching in Cisco U.
Discover AI studying and begin constructing your expertise at present.
Learn extra from the AI Break sequence:
Join Cisco U. | Be part of theCisco Studying Community at present without spending a dime.
Study with Cisco
X | Threads | Fb | LinkedIn | Instagram | YouTube
Use #Ciscou and#CiscoCert to hitch the dialog.
Share:
