Course · Training · Workshop
Agentic (AI-Assisted) System Engineering
System engineering with agentic workflow: Peer-engineering approach with generative AI for Ansible, shell scripting, GitOps, infrastructure as code, and server automation.
This innovative course introduces agent-based system engineering practices where AI functions as an active peer engineer. Participants learn how to establish continuous collaboration with established agentic coding tools, where the AI directly creates Ansible playbooks, optimizes shell scripts, develops infrastructure-as-code modules, and automates server configurations. The course covers advanced strategies such as planning & acting phases, rules formulation, prompt techniques, and context management specifically for system engineering. Participants will work with real infrastructure projects including Ansible automation, Bash/Python scripting, GitOps workflows, infrastructure as code (Terraform, OpenTofu), configuration management, and server orchestration. The course will look at fixing automation issues, debugging playbooks and scripts, implementing new infrastructure automations, and building a project-specific agentic system engineering framework.
What participants say
These customers booked courses in the same topic cluster.More customers →
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 system engineering technologies and practices. For in-house courses there is a selection of tools and platforms which can be chosen to better fit the audience.
– Introduction to Agentic System Engineering:
- Evolution from “one-shot prompting” to agentic workflow peer engineering
- Understanding the agentic workflow paradigm for system engineering
- Overview of course environment and tools – Fundamentals of IDE-Integrated AI Agents for System Engineering:
- Setting up and configuring the IDE extension
- Understanding planning vs. acting modes for infrastructure tasks
- Effective communication patterns with AI agents for system engineering tasks – Context Management for System Engineering:
- Building effective infrastructure project context
- Defining clear rules for automation and configuration management
- Advanced prompt engineering techniques for system engineering – Ansible Automation with AI Agents:
- Ansible playbook development and optimization
- Creating Ansible roles and collections
- Inventory management and dynamic inventories
- Ansible Vault for secret management
- Debugging and testing Ansible playbooks – Shell Scripting and Automation with AI Agents:
- Bash script development and best practices
- Python scripts for system automation
- Error handling and logging in scripts
- Script testing and validation
- Cron jobs and systemd timer configuration – Infrastructure as Code with AI Agents:
- Terraform/OpenTofu modules for server infrastructure
- State management and remote backends
- Provider configuration for different platforms
- IaC testing and validation – Configuration Management and Server Orchestration:
- Server configuration with Ansible
- Automating package management and updates
- User and permission management
- Service management and systemd units
- Firewall configuration (iptables, firewalld, ufw) – GitOps Workflows for System Engineering:
- Git-based infrastructure management
- Declarative configuration management
- Automated deployment and rollback strategies
- Version control for infrastructure code – Monitoring and Logging Automation:
- Configuring log rotation and aggregation
- Monitoring agent deployment (Prometheus Node Exporter, etc.)
- Alert configuration and notification setup
- Performance monitoring and tuning – Backup and Disaster Recovery Automation:
- Developing backup scripts and strategies
- Automated backup testing
- Disaster recovery playbooks
- Snapshot management for VMs and volumes – Security and Compliance Automation:
- Security hardening with Ansible
- Automated security scanning and patching
- Automating compliance checks (CIS Benchmarks)
- SSH key management and rotation – Use and Build MCP Servers for System Engineering:
- Understanding the Model Context Protocol
- Integrating server management APIs
- Custom tools for SSH interaction and remote execution
- Integrating external infrastructure services – Cloud and Hybrid Infrastructure:
- Cloud provider integration (AWS EC2, Azure VMs, GCP Compute)
- Hybrid cloud automation
- Multi-cloud management strategies
- Cloud-init and user-data scripts – 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 legacy systems and migration
- Error recovery and iterative improvement – Building Project-Specific “Agentic System Engineering Framework”:
- Sharable rules, context and tooling for teams
- Agentic empowering testing setup for infrastructure
- AI-powered dev-containers for system engineering – Best Practices and Future Trends:
- Emerging technologies in AI-assisted system engineering
- Security considerations for agentic infrastructure automation
- Team collaboration with AI agents in system engineering 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.
The actual course content may differ from the above depending on the trainer, delivery, duration and the composition of participants.
Request this course in-house
Request a public date
No suitable public date? Register without obligation — once there is enough interest we schedule a new public date and let you know first.
More about Agentic System Engineering
The agentic workflow in system engineering represents a paradigm shift in how we approach infrastructure automation. With modern AI tools, we establish a working method where AI agents not only make suggestions but actively participate in the engineering process by directly creating Ansible playbooks, optimizing shell scripts, and developing infrastructure-as-code modules. This peer engineering method combines the expertise of human system engineers with the efficiency and analytical strength of AI systems.Further resources:
History
The idea of using AI agents for infrastructure automation has its roots in autonomous agent research from the 1990s. With the rise of large language models and frameworks like LangChain and AutoGen, it became practically feasible starting in 2023 to integrate AI agents directly into system engineering workflows.
Today, specialized agentic coding tools like Claude Code by Anthropic and GitHub Copilot Workspace allow AI agents not just to suggest code, but to autonomously plan and execute full infrastructure tasks – including Ansible playbook development, IaC module creation, and GitOps workflows. This evolution has shaped the concept of "peer engineering," where humans and AI collaborate as equals throughout the infrastructure automation lifecycle.