Content:

The course will consist of the following topics and may be extended or adapted based on the audience.
The examples in the course will focus on widely used platform and DevOps technologies.
For in-house courses there is a selection of tools and platforms which can be chosen to better fit the audience.

– Introduction to Agentic Platform & DevOps Engineering:
... - Evolution from "one-shot prompting" to agentic workflow peer engineering
... - Understanding the agentic workflow paradigm for infrastructure engineering
... - Overview of course environment and tools
– Fundamentals of IDE-Integrated AI Agents for DevOps:
... - Setting up and configuring the IDE extension
... - Understanding planning vs. acting modes for infrastructure tasks
... - Effective communication patterns with AI agents for DevOps tasks
– Context Management for Platform Engineering:
... - Building effective infrastructure project context
... - Defining clear rules for infrastructure as code
... - Advanced prompt engineering techniques for DevOps
– CI/CD Pipeline Engineering with AI Agents:
... - Creating and optimizing GitHub Actions workflows
... - GitLab CI/CD pipeline configuration and debugging
... - Jenkins pipeline-as-code with Groovy and Jenkinsfile
... - Pipeline testing and validation
– Container Engineering and Docker:
... - Dockerfile creation and optimization
... - Multi-stage builds and best practices
... - Container image scanning and security
... - Docker Compose for local development environments
– Kubernetes Engineering with AI Agents:
... - Kubernetes manifest generation (Deployments, Services, ConfigMaps)
... - Creating and customizing Helm charts
... - Kustomize configurations for different environments
... - Debugging Kubernetes deployments and pod issues
– GitOps Workflows and Continuous Deployment:
... - ArgoCD application configurations
... - Flux GitOps setup and automation
... - Declarative infrastructure management
... - Automated rollbacks and progressive delivery
– Infrastructure as Code with AI Agents:
... - Developing and testing Terraform/OpenTofu modules
... - State management and remote backends
... - Crossplane for Kubernetes-native infrastructure
... - IaC testing with Terratest or similar tools
– Monitoring, Logging, and Observability:
... - Prometheus configurations and alert rules
... - Creating Grafana dashboards
... - OpenTelemetry integration
... - Log aggregation with ELK/Loki
– Use and Build MCP Servers for DevOps:
... - Understanding the Model Context Protocol
... - Integrating cloud provider APIs (AWS, Azure, GCP)
... - Custom tools for Kubernetes interaction
... - Integrating external DevOps services
– Security and Compliance Automation:
... - Policy-as-code with OPA/Gatekeeper
... - Secret management with Vault or similar tools
... - Security scanning in CI/CD pipelines
... - Automating compliance checks
– Model Selection and Deployment:
... - Comparing different AI models for infrastructure tasks
... - Cloud providers vs. self-hosting considerations
... - Performance and cost optimization
– Advanced Agent Interaction Techniques:
... - Multi-step reasoning for complex infrastructure changes
... - Handling multi-cloud requirements
... - Error recovery and iterative improvement
– Building Project-Specific "Agentic Platform Engineering Framework":
... - Sharable rules, context and tooling for teams
... - Agentic empowering testing setup for infrastructure
... - AI-powered dev-containers for platform engineering
– Best Practices and Future Trends:
... - Emerging technologies in AI-assisted platform engineering
... - Security considerations for agentic infrastructure automation
... - Team collaboration with AI agents in DevOps context

The course focuses on a well established, open source, vendor and model provider independent AI integration in Visual Studio Code. Alternative AI focused IDE's, Plugins or Integrations will be discussed. The concepts, workflows and approaches are transferable to any tool with similar or stronger capabilities.

Disclaimer: The actual course content may vary from the above, depending on the trainer, implementation, duration and constellation of participants.

Whether we call it training, course, workshop or seminar, we want to pick up participants at their point and equip them with the necessary practical knowledge so that they can apply the technology directly after the training and deepen it independently.