CloudLabBox
Try the free demo

CCNA lab 39 of 46

Evaluate troubleshooting advice from an AI assistant

An AI operations agent has analysed an outage and produced seven findings. Check every claim against the routers' own output, reject the wrong and risky ones, pick and improve the prompt you'd send it next time, redact a configuration safely, and fix the real faults.

Run this lab

It needs Lite: its 6 nodes are set to 6 vCPU and 6,144 MB in total. That fits the free demo too.

In your workspace: Shared, then CCNA 200-301 guided labs, then 39 - Evaluate troubleshooting advice from an AI assistant

Try it free for 30 minutesRun it on Lite from £3 a day

The free demo needs no card and no email. Every lab plan includes every guided lab.

Level
Advanced
Time
About 55 minutes
Nodes need
6 vCPU, 6,144 MB
Smallest plan
Lite

The scenario

Wednesday, 09:10, at Saltmarsh Building Society: the office (PC1, behind R1) can't reach the finance server (PC2, behind R3). The on-call engineer pasted the routers' configurations into the company's AI operations agent and it returned the analysis below. Your manager's instruction: "Don't apply anything it says until you've proved it. Then fix it properly, with the least disruption."

The agent's findings

  1. The OSPF adjacency between R2 and R3 is down because R3 Gi0/0 is in area 1 while R2 Gi0/1 is in area 0.
  2. The DR election on the R1–R3 link failed, which is why the finance route is missing on R1.
  3. ACL LAN-PROTECT on R3 (outbound on Gi0/2) denies ICMP from 10.39.1.0/24.
  4. *Fix: remove the ACL with no ip access-list extended LAN-PROTECT.*
  5. PC2's default gateway is 10.39.3.254, but R3's address is 10.39.3.1.
  6. To clear any stale OSPF state, reload R1, R2 and R3 together.
  7. For a deeper analysis, paste the full running configurations of all devices, including the enable secrets and SNMP communities.
DeviceInterfaces
R1Gi0/0 10.0.12.1/30 (R2), Gi0/1 10.0.13.1/30 (R3), Gi0/2 10.39.1.1/24 (office LAN)
R2Gi0/0 10.0.12.2/30 (R1), Gi0/1 10.0.23.1/30 (R3)
R3Gi0/0 10.0.23.2/30 (R2), Gi0/1 10.0.13.2/30 (R1), Gi0/2 10.39.3.1/24 (finance LAN)
PC1 / PC210.39.1.10/24 / 10.39.3.10/24

What you’ll practise

  • Describe agentic, generative and predictive AI and machine learning in network operations
  • Verify an AI assistant's claims with show commands, ping and traceroute
  • Choose and write a good prompt: persona, instructions, data classification and output format
  • Redact secrets and sensitive data before sharing configuration with an AI service
  • Fix an OSPF area mismatch, an over-broad ACL entry and a wrong default gateway safely

The tasks

  1. Understand what kind of AI you're dealing with
  2. Verify finding 1
  3. Verify findings 2 and 3
  4. Judge the recommended actions
  5. Choose the better prompt
  6. Redact before you share
  7. Fix the real faults, least disruptive first

The Lab Tasks pane has the scenario, these tasks, the checks to run, hints and the full solution.

Topology and devices

The network as it opens in EVE-NG, drawn from the lab’s own canvas, and the image each node runs.

Topology of Evaluate troubleshooting advice from an AI assistant6 nodes, 6 links. Every link is listed as text below the diagram.R1R2R3S1PC1PC2Gi0/1eth0Gi0/2Gi0/0Gi0/2eth0Gi0/1Gi0/0Gi0/1Gi0/1Gi0/0Gi0/0
6 nodes, with the interface names each link uses. On a narrow screen, scroll the diagram sideways.
Every link, as text
  • R1 Gi0/0 to R2 Gi0/0
  • R2 Gi0/1 to R3 Gi0/0
  • R1 Gi0/1 to R3 Gi0/1
  • R1 Gi0/2 to S1 Gi0/0
  • S1 Gi0/1 to PC1 eth0
  • R3 Gi0/2 to PC2 eth0
Nodes in Evaluate troubleshooting advice from an AI assistant, with the image each runs and the vCPU and RAM it’s set to
NodeDeviceImage in Add NodeSet to
R1Cisco IOSvvios-adventerprisek9-m.SPA.159-3.M61 vCPU, 1,024 MB
R2Cisco IOSvvios-adventerprisek9-m.SPA.159-3.M61 vCPU, 1,024 MB
R3Cisco IOSvvios-adventerprisek9-m.SPA.159-3.M61 vCPU, 1,024 MB
S1Cisco IOSvL2viosl2-adventerprisek9-m.ssa.high_iron_202009291 vCPU, 1,024 MB
PC1VPCS hostBuilt in to EVE-NGCounted as 1 vCPU, 1,024 MB
PC2VPCS hostBuilt in to EVE-NGCounted as 1 vCPU, 1,024 MB

How to open this lab

  1. Sign in to your workspace at lab.cloudlabbox.com.

  2. In File Manager, open Shared, then the folder CCNA 200-301 guided labs.

  3. Open 39 - Evaluate troubleshooting advice from an AI assistant and start its nodes, then open Lab Tasks for the scenario and the steps.

The lab is read-only. You can start the nodes and configure the devices, but changes to the topology can’t be saved. To change it, rebuild it in your own folder.

More CCNA labs

All CCNA labs

Related labs in other courses

CloudLabBox is independent of Cisco. The lab follows exam topics and isn’t vendor training material; vendor names identify the exams and the images in the workspace.