Core Principles

Garbage In, Garbage Out (GIGO)

AI output quality depends entirely on the quality of the input.

DO DO NOT
  • Provide clear, accurate, and complete prompts
  • Include relevant technical context and constraints
  • Verify configuration examples before implementation
  • Use vague or incomplete prompts
  • Assume AI understands your environment automatically
  • Paste sensitive customer or production data into public AI tools

Writing Effective Prompts – SCOPE Framework

Use the SCOPE framework to improve AI response quality and consistency.

SCOPE

  • S — Situation: Describe the environment, background, or technical context
  • C — Character: Define the role the AI should act as
  • O — Output: Specify the desired response format
  • P — Purpose: Clearly explain the goal or task
  • E — Examples: Provide examples of expected input/output where possible

Example Prompt

Situation: ISP hosting environment running Ubuntu 24.04 and NGINX
Character: Act as a senior Linux systems administrator
Output: Return a commented Bash script with a short explanation
Purpose: Create a disk monitoring script that alerts when usage exceeds 85%
Examples: Use syslog formatting similar to existing monitoring scripts

Prompt Best Practices

DO DO NOT
  • Provide clear technical context
  • Define the expected output format
  • Include examples where possible implementation
  • Specify versions, limitations, and constraints
  • Use vague or incomplete prompts
  • Assume AI understands your infrastructure
  • Share passwords, API keys, or customer data
  • Deploy AI-generated output without validation and testing

Human in the Loop (MITL)

AI assists humans — it does not replace engineering judgement.

DO DO NOT
  • Review all AI-generated configurations, scripts, and documentation
  • Require human approval before production deployment
  • Validate outputs in staging or lab environments first
  • Allow AI-generated changes directly into production
  • Treat AI responses as authoritative without verification
  • Use AI as the sole decision-maker for operational or security changes

Approval & Change Control

All AI-assisted work must follow existing operational governance.

DO DO NOT
  • Follow standard change management and CAB procedures
  • Clearly identify when AI contributed to a deliverable
  • Maintain audibility for AI-assisted operational changes
  • Bypass approval workflows because “AI suggested it”
  • Deploy untested AI-generated automation
  • Skip peer review for AI-created configurations or scripts

Documentation Requirements

Prompt Documentation

Important prompts used for operational work should be documented.

Include:

  • Purpose of the prompt
  • AI tool used
  • Date generated
  • Reviewer/approver
  • Final validated output

AI-Generated Documentation

Documents produced fully or partially by AI must be marked appropriately.

Security & Data Protection

Never Upload:

  • Customer data
  • Passwords, API keys, certificates, or secrets
  • Internal IP schemes or sensitive network diagrams
  • Confidential business information
  • Use only company-approved AI platforms for operational work.

CCNA V2.0

Cisco announced CCNA 2.0 changes to include 10% weighed topic, for following headlines:

    • Describe the role of agentic AI in network operations
    • 5.2 Select a prompt to send to a generative AI system to support network operations considering prompt components such as data classification, output format, persona, and instructions
    • 5.3 Describe network management approaches (device-based, cloud-based, controller-based, automation-based, and infrastructure as code)
    • 5.4 Describe the function of SNMP in network operations
    • 5.5 Use configuration management mechanisms such as Ansible to execute commands
    • 5.6 Interpret syslog message content, severity levels, and facilities