Get began with the Deep Community Mannequin AI Assistant in Cisco U.

At Cisco Stay in San Diego, D.J. Sampath, Senior Vice President of Cisco’s AI Software program and Platform group, wowed the group with a demo of AI Canvas. That’s a multi-data, multi-agent system, built-in with Cisco’s AI Assistant and powered by Cisco’s Deep Community Mannequin. In that demo, we might all see AI Canvas’s capacity to hurry troubleshooting, convey siloed groups collectively, and allow automation throughout the complete stack.

AI Canvas gained’t be obtainable till October. Nonetheless, we wished to supply our CCIEs, CCDEs, and Cisco Licensed DevNet Specialists the chance to work with the Deep Community Mannequin as quickly as potential. So we’re making the mannequin obtainable to CCIEs and different consultants by means of an AI Studying Assistant obtainable in Cisco U.

We predict CCIEs (and shortly, different community engineers) will discover a wealth of ways in which the Deep Community Mannequin can assist them study extra and grow to be extra environment friendly. However we notice that agentic ops is model new, and that you simply is likely to be questioning how one can instantly begin experimenting with the Deep Community Mannequin. So I believed I’d provide some pattern use circumstances that can assist you get began.

Tailor-made eventualities and coaching paths

As a CCIE, you’ve received years—typically many years—of expertise in networking, and also you’re absolutely on top of things in your group’s IT infrastructure. However what about your staff members, particularly extra junior community engineers? The Deep Community Mannequin AI Assistant can be utilized to construct tailor-made eventualities and coaching concepts so that everybody in your staff can study the talents wanted for the community you at the moment have, in addition to any new applied sciences your group plans to roll out.

The Deep Community Mannequin understands a variety of networking applied sciences, nevertheless it’s educated explicitly on a depth and breadth of Cisco-specific materials. It’s additionally educated on the supplies and coursework obtainable in Cisco U. You would possibly strive a immediate corresponding to this one:

• I’m the tech lead for a small staff of community engineers. I must shortly get them on top of things on the networking expertise we use in our surroundings, together with BGP, MPLS, and OSPF. Might you construct me a customized examine plan?

Once I requested this query of the Deep Community Mannequin AI Assistant, I received a really good syllabus in define kind, with hyperlinks to programs in Cisco U.

Right here’s a pattern:

Design validation and optimization

Cisco Validated Designs (CVDs) are primarily blueprints, and IT professionals are accustomed to working by means of them. However typically you want extra steering. The Deep Community Mannequin AI Assistant can assist make CVDs extra navigable. It will possibly entry different sources to assist flesh out CVDs and provide ideas for bettering or optimizing designs.

It will possibly additionally summarize the CVD, providing you with a high-level overview earlier than studying the entire thing. You may ask it questions corresponding to:

• Contemplating the CVD for FlexPod, present a getting-started doc that I can use to configure my preliminary UCS supervisor.
• I’m starting to implement the CVD for FlexPod. Might you give me a high-level overview of what I’ll be doing and the items I’ll be working with?

The Deep Community Mannequin AI Assistant can assist validate an present design with respect to a CVD and provide ideas for bettering or optimizing designs.

• What sort of storage expertise ought to I think about for booting my blades in a UCS B chassis?

In the event you’re having points with a CVD, you’ll be able to ask the Deep Community Mannequin AI Assistant the place it is best to begin trying.

Automation assistant

The Deep Community Mannequin AI Assistant also can assist with automation. You would ask it questions corresponding to:

• I’m an professional in community structure and wish some assist automating our department SD-WAN deployment. What can be a well-supported, easy-to-learn device that might assist me help this? My staff doesn’t have quite a lot of coding expertise. Might you present examples and hyperlinks to related documentation and coaching?

Troubleshooting

The Deep Community Mannequin AI Assistant can assist analyze community diagnostics, corresponding to syslog messages and debug output, and study drawback signs to offer perception that is likely to be missed by human eyes. Though generative AI continues to be a younger expertise that may make errors, expert-level IT professionals are well-equipped to guage the output for accuracy and detect hallucinations.

For instance, the Deep Community Mannequin AI Assistant might assist interpret a syslog message. You would merely enter the message into the assistant and say you want recommendation or a spot to start out. As a result of it’s educated on Cisco’s syslog codecs, it can provide steering and cross-reference different information.

In the event you’re working with a number of information sources, the evaluation turns into extra advanced. With the Deep Community Mannequin AI Assistant, you’ll be able to describe the symptom you see after which ask, “What ought to I search for?” (After all, it is best to at all times watch out about pasting uncooked output into AI.) On this manner, you should use the assistant to information you to the purpose the place you’re snug taking up.

Quite a lot of debugging is actually taking a look at various kinds of diagnostic information and trying to find the needle in a haystack that can assist you already know what to do subsequent. The Deep Community Mannequin AI Assistant can assist with that course of. For instance, if it’s essential to troubleshoot routing adjacencies, you’ll probably want to collect information from a number of units and correlate the information to establish a root trigger.

You are a community troubleshooting assistant. Assist me diagnose why my OSPFv3 session just isn’t establishing with one neighbor. That is the output from ‘present ospfv3 neighbor’:

          OSPFv3 1 address-family ipv6 (router-id 192.0.2.1)

Neighbor ID     Pri   State           Useless Time   Interface ID    Interface

192.0.2.2    128   EXCHANGE/BDR    00:00:38    13              Vlan300

192.0.2.6    128   FULL/DR         00:00:37    5               Vlan300

And that is the related config from Vlan300: 

ipv6 deal with FE80::300:241 link-local

ipv6 deal with 2001:DB8::241/64

ipv6 allow

ipv6 mtu 1500

ipv6 nd dad makes an attempt 0

ipv6 nd ra suppress all

no ipv6 redirects

ipv6 ospf 1 space 0

bfd interval 1000 min_rx 1000 multiplier 5

Right here’s the response I received:

In some unspecified time in the future, many people find yourself troubleshooting on the protocol degree (packet seize or it didn’t occur, proper?), the place issues get advanced in a short time. On this case, you’ll be able to paste the decoded output of a packet seize (corresponding to that from Wireshark or Tshark) to the Deep Community Mannequin AI Assistant, which might break down the body particulars for you. It will possibly establish hard-to-spot points and dramatically improve the efficacy of deep networking troubleshooting.

The AI assistant can provide you extra which means and context than you would possibly get with different instruments. I attempted this with a problematic SNMPv3 packet. The AI assistant regarded on the worth of the fields and defined them to me. Whereas Wireshark confirmed me the sphere names, the AI assistant defined that one area, the msgAuthoritativeEngineTime, represented the variety of seconds a tool had been on-line, which was 61411 (roughly seven weeks). The factor is, I simply booted that system. So my SNMP supervisor was confused, and the SNMPv3 entice wasn’t being trusted. Bug discovered!

Whereas most of us are fairly acquainted with a variety of community applied sciences, we will not be consultants in each one of many protocols we run on our community. Subsequently, think about how helpful this may be for a protocol you’re not extremely educated about on the area degree. The AI assistant is great at analyzing these fields and explaining their network-relevant context. Whereas the assistant gained’t clear up the issue for you, when used correctly, it can provide you some good hints. When you perceive extra about these fields, making use of some reasoning and fixing the bug is far simpler.

These are simply a few of the ways in which the Deep Community Mannequin AI Assistant may very well be useful to skilled community engineers. I hope they’re a helpful springboard to your pondering. In the event you strive them out, I’d be excited to listen to in regards to the outcomes you’re getting.

However I’d be much more excited to listen to about use circumstances you’ve provide you with that I’d by no means consider. AI is an extremely highly effective device that may make us extra environment friendly and, frankly, much less confused. However we should determine the most effective methods to make use of them, and we’re all on that journey collectively.

Join Cisco U. | Be a part of the  Cisco Studying Community at this time without cost.

Study with Cisco

X | Threads | Fb | LinkedIn | Instagram | YouTube

Use  #CiscoU and #CiscoCert to affix the dialog.

Share: