Platform Engineer AI Alumni Course
AI content description
This course leverages AI tools in modern platform engineering tasks (e.g., DevOps pipelines, Infrastructure as Code, monitoring, security scanning). Learners will learn how to integrate AI assistance for analysing logs, troubleshooting systems, automating configurations, detecting vulnerabilities, and optimizing performance or costs. Emphasis is placed on responsible AI usage, including security/privacy best practices, ethical considerations, and collaboration with human experts for final review. Hands-on labs and real-world scenarios ensure that learners can apply AI-augmented workflows confidently and safely in production-like environments.
Tools You Will Explore
- GitHub
- Copilot
- ChatGPT
- Aider
- Cline
- Prometheus
- Grafana Cloud AI
Modules
➤ Introducing: Artificial Intelligence in the IT World (0.5 hours)
- Understand the basics of artificial intelligence and its key concepts
- Distinguish between the different types of artificial intelligence, such as chatbots and agentic AI
- Test previous knowledge of AI concepts to identify knowledge gaps
➤ Analytical Thinking & Productivity in the Age of AI (~0.75 hours)
- Understand the structure of the analytical thinking process
- Identify how AI can be used at various stages of the analytical thinking process
- Understand the use of AI in IT roles to increase productivity
- Evaluate the appropriateness of AI tools for solving specific problems
➤ Communicating with AI (~0.75 hours)
- Recognise the limitations and risks of AI use in professional settings
- Evaluate examples of ethical vs non-ethical use of AI in professional settings
- Explore different approaches to prompting to communicate effectively with AI
- Practise drafting a README file with the help of AI
➤ AI Tools Overview for Platform Engineers (~1 hour)
- Identify common AI tools for DevOps tasks
- Explain how AI reduces manual workload in platform engineering
- Assess risks associated with AI reliance
➤ AI for Logs, Alerts & Basic Troubleshooting (~1.5 hours)
- Demonstrate AI-driven analysis of Kubernetes/Docker logs
- Interpret and validate AI-generated troubleshooting suggestions
- Decide when to escalate AI troubleshooting results
➤ Basic Introduction to IaC and AI (~1.5 hours)
- Explain what Infrastructure as Code (IaC) is in simple terms and provide basic examples
- Recognize common benefits of using IaC in platform engineering tasks (e.g., consistency, automation, reproducibility)
- Identify simple ways AI can support beginners to create basic infrastructure automation scripts
➤ AI-Driven Debugging & Testing (~0.75 hours)
- Utilize AI tools for parsing and debugging stack traces
- Create effective test scripts using AI-driven TDD approach
- Evaluate AI debugging suggestions critically
➤ Responsible AI Usage & Escalation (~1 hour)
- Identify security/privacy pitfalls of AI
- Demonstrate secure practices when using AI tools
- Formulate escalation procedures for risky AI recommendations
➤ AI-Driven Security & Vulnerability Scanning (~1.5 hours)
- Scan container images/config files using AI tools
- Interpret vulnerabilities identified by AI tools
- Prioritise security fixes recommended by AI
➤ AI-Assisted Performance Tuning & Cost Optimisation (~1.5 hours)
- Identify resource inefficiencies using AI analysis
- Assess recommendations for performance and cost trade-offs
- Formulate actionable steps based on AI’s optimisation advice
➤ End-to-End Deployment & Testing (~1.5 hours)
- Integrate AI tools throughout the platform engineering workflow
- Evaluate outcomes of AI-supported project tasks critically
- Reflect on AI tool selection effectiveness