“The shift for builders is extra radical than we predict.”
— Jeetu Patel, President and CPO, Cisco
AI is operating full throttle, leaving a wake of radical modifications 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 weblog, I described MCP—Mannequin Context Protocol—and the way agentic AI might lastly communicate our language, perceive our networks, and take significant motion. Now I wish 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 some of the irritating points in community operations: configuration drift.
Let’s break down the method of constructing 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 software integration—it’s that the agent could make autonomous choices 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 gadget connectivity points or standing modifications within the final 4 hours.”
- “Present me all community configuration modifications 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—underneath 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 surroundings—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 a superb immediate to start out:
Immediate > I must see what’s occurring with my Meraki community. Are you able to present me the newest Splunk alerts, particularly within the meraki_index? I would like 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 must be particular about the best way 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 whole Meraki Index to know the information construction and accessible sources.
- Information evaluation – Discovered two essential sources: “House Community” (port occasions) and “Meraki Community” (config modifications).
- Focused extraction – Targeted particularly on “Meraki Community” supply as requested.
- Alert parsing – Extracted key fields: alert varieties, ranges, units, and alter particulars from JSON payload.
This was all by itself, together with the self-correction and retries to get the outcome 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, gadget IP deal with 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 write down a hardcoded if-then movement between the 2. I simply outlined the instruments and gave the agent context. The agent selected the suitable software, chosen the proper operate, and acted totally autonomously.
- I outlined the instruments decorators to make accessible in my Meraki MCP–nothing earth-shattering–easy features that execute one factor and one factor solely—get an inventory of my units, replace my units, and so forth— all of which community engineers have doubtless used and coded.
That is what occurs whenever 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 includes actual output].
First, we’ll get a diff of what was modified
Immediate > This Kareem Iskander dude shouldn’t have made any modifications 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 data is being pulled from Splunk by means of the Splunk MCP server. Additionally, discover how our agent gave us ideas on the best way to revert the modifications. As soon as once more, spectacular! Discover that the data is being pulled from Splunk utilizing the Splunk MCP server.
Additionally, discover how our agent gave us ideas on the best way to revert the modifications mechanically utilizing the accessible API endpoints within the Meraki MCP! I didn’t should specify which Meraki group or which community the units belong to, nor did I’ve to specify the gadget 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 authentic state for all of the modifications you’ve detected!
Why this issues
This isn’t only a enjoyable facet challenge. It addresses an actual ache level for all community engineers: configuration drift!
Whether or not it’s unintentional modifications, unauthorized edits, or misalignment with the supply of reality, config drift results in downtime, compliance points, and countless handbook cleanup. Agentic AI affords a greater mannequin: detect, perceive, and repair mechanically.
I simply took two steps and let the agent run with it:
- Outline the software interfaces (Splunk SDK + Meraki API)
- Register these instruments with MCP
That is the facility of constructing agentic methods on high of the workflows we already know.
What abilities do you really want?
Let’s preserve it actual. Listed below are the talents required:
- Coding with Python
- Understanding SDKs and the best way to use them
- Community automation and programmability with APIs
- MCP framework to construction software entry and execution
- Networking abilities
The place that is all going
Let’s zoom out for a second to higher perceive the large 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 announcement, Cisco laid the muse 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 means of Splunk, one other acts by means of Meraki—all with only a immediate and some registered software features.
Now think about layering in Cisco’s Deep Community Mannequin—a complete, machine-readable understanding of your complete community, educated on years of CCIE-level Cisco experience and telemetry, and a set of pre-built brokers prepared out of the field.
As an alternative of merely reversing a misconfigured VLAN, the agent understands:
- Which purposes depend 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 important enterprise visitors
- The best way to replace the supply of reality to mirror any reliable intent behind the change
That is the place the idea turns into a actuality:
- AI Canvas offers us the surroundings and brokers.
- The Cisco Deep Community Mannequin offers brokers the situational intelligence to behave with context.
- MCP offers us the extendibility to BYOA (deliver/construct your individual agent, which is a future characteristic).
And that’s what community engineers want—not one other platform, however an assistant that will get it; one that may cause like us, function sooner than us, and make choices we belief.
It’s time to take a seat 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 stated, “The longer term is coming sooner 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 expertise with synthetic intelligence coaching in Cisco U.
Discover AI studying and begin constructing your abilities at present.
Learn extra from the AI Break sequence:
Join Cisco U. | Be a part of the Cisco Studying Community at present without cost.
Be taught with Cisco
X | Threads | Fb | LinkedIn | Instagram | YouTube
Use #CiscoU and #CiscoCert to affix the dialog.
Share:
