
1- Artificial Intelligence (AI)
2- Machine Learning (ML)
3- The relationship between AI and ML
4- Contrasting Traditional Programming with Machine Learning
5- Key ML processes: Learning, Reasoning, and Self-Correction
6- Types of Data used in ML (Images, Text, Numerical)
7- Functions of ML systems: Descriptive, Predictive, and Prescriptive
1- Supervised Learning
2- Unlabeled Data
3- Reinforcement Learning
4- Labeled Data
5- Anomaly Detection
6- Trial-and-Error Learning
7- Pattern Recognition
1-Predictive Maintenance
2-Anomaly Detection and Security
3-Traffic Analysis and Management
4-Automated Configuration and Management
5-Root Cause Analysis
6-Proactive Management
7-Quality of Service (QoS)
1-Predictive AI
2-Generative AI
3-Generative Pre-Trained Transformer (GPT)
4-Publicly Available GPT Models
1-Importance of Question Phrasing
2-How LLMs Interpret Language Relationships
3-Role of Vocabulary and Clarity in AI Prompts
4-Example: Network Engineering and Specific Prompts
1- Hallucination in LLMs
2- Why retraining is not always enough
3- Retrieval-Augmented Generation (RAG) overview
4- RAG pipeline: indexing → retrieval → generation
5- Using RAG with ChatGPT (uploading docs)
6- RAG limitations and caveats
7- Best practices to reduce inaccuracies
1- The Challenge of Network Automation
2- How GPT Helps You Write Code Without Knowing the Language
3- Ansible and YAML Overview
4- Using GPT to Generate Automation Code
5- Beyond YAML , Generating Python Code
1- Why Network Error Messages Are Confusing
2- How GPT Helps You Translate and Solve Errors
3- Why GPT Is Useful for Engineers
4- Real-World Scenario Example
5- GPT as a Learning Partner
1-Large Language Models (LLMs)
2-Limitations of LLMs
3-Cisco AIOps Solutions
4-Predictive Maintenance
5-Anomaly Detection
6-Dynamic Traffic Management
7-Integration of LLMs with Cisco AIOps
1-Cisco AIOps Overview
2-Cisco Catalyst Center
3-Cisco Nexus Dashboard & Insights
4-Cisco Meraki
5-Cisco AppDynamics
6-Cisco ThousandEyes
7-Cisco Secure Network Analytics
1-Public vs. Private GPT Instances
2-Data Sensitivity: What to Share and What Not to Share
3-Prompt Injection Attacks
4-Real-World Example: The Code Injection
5-Strengthening Security with Audits and Access Controls
1-What is AIOps?
2-Why AIOps is Different
3-How AIOps Works
4-AIOps and Cisco
5-Why Learn AIOps?
6-Benefits for Network Engineers
1-Introduction to Cisco’s AIOps Vision
2-AgenticOps Framework
3-Cisco’s AIOps Tools
4-Real-World Applications
5-Business and Operational Benefits
6-Future-Proofing Network Skills
1-Introduction to Cisco AIOps Tools
2-Cisco DNA Center: The Central Hub for Network Assurance
3-ThousandEyes: End-to-End Visibility and Observability
4-AppDynamics: Application Performance and Business Impact
5-Integration and Why These Tools Work Together
6-Challenges and Considerations
7-Future of Cisco AIOps Tools
1-Transforming Network Operations
2-From Reactive to Proactive
3-AIOps in Networking
4-The AIOps Advantage
5-Beyond Human Scale
6-AIOps Unleashed
7-The Silent Network Revolution
8-Future-Proofing Networks
9-From Alert Storms to Actionable Insights
10-The Business Case for AIOps in Networking
1-Traditional Network Operations: The Old Way
2-The Rise of AIOps: A New Era
3-Cisco's AIOps Tools: Driving the Evolution
4-Cisco DNA Center: The Intelligent Core
5-ThousandEyes: Seeing Beyond the Network
6-AppDynamics: Application-Centric Management
7-The Impact of AI-Driven Operations
8-Practical Scenario
9-Why This Evolution Matters
1-What is AgenticOps?
2-Evolution from AIOps to AgenticOps
3-Core Components of AgenticOps
4-Deep Network Model
5-Cisco AI Assistant
6-AI Canvas
7-Benefits of AgenticOps
8-Practical Scenario
1-AIOps Core Pillars
2-Ingestion Introduction
3-Topology Introduction
4-Correlation Introduction
5-Recognition Introduction
6-Remediation Introduction
1-Evolution to Full-Stack Observability (FSO)
2-Traditional Monitoring – Per Domain, Availability Focused
3-Enhanced Visibility – Still Per Domain, Performance Focused
4-Full-Stack Observability (FSO) – Cross-Functional, Experience Focused
5-FSO and Contextual Insights
6-Key Benefits of Cisco FSO
1-Cisco’s Observability Platform versus a standalone AIOps tool
2-Data Sources
3-Data Types and Context
4-Alerting and Noise Reduction
5-Anomaly Detection and Root Cause
6-Business Value
Welcome to AI Fundamentals for Network Engineers, a comprehensive course designed to bridge the gap between artificial intelligence and modern network operations. This course introduces network engineers to the core concepts of AI and machine learning, exploring how these technologies are revolutionizing network management, automation, and security. You’ll start by understanding AI fundamentals, the different ways AI learns, and the types of AI that are shaping the future of networking. Practical topics such as prompt engineering, reducing hallucinations for accurate answers, and leveraging AI to simplify network automation are also covered. Additionally, students will gain insights into understanding network errors with AI, the limits of large language models, and Cisco’s innovative Smart AI solutions for smarter, more secure networks.
The course also provides a deep dive into Cisco AIOps, detailing its vision, tools, and how AI-driven operations are transforming traditional network management. Key topics include agentic operations, full-stack observability, the core pillars of AIOps, and a comparison of Cisco Observability Platform versus standalone AIOps solutions.
Please note that this course is currently under construction, and more content and advanced topics will be added over time. As the course evolves, learners can expect to gain an even deeper understanding of how AI can optimize, automate, and secure networks, ensuring they stay ahead in the rapidly evolving world of network engineering. Whether you are a beginner or an experienced engineer, this course provides the foundational knowledge and practical insights needed to harness AI effectively in your network operations.