Agentic Software Engineering (Online) - André Deuerling, Torben Keller - German
Generative AI is changing how we develop software - from individual code snippets to complete, agent-driven development processes. In this three-day training course, you will learn how to harness this transformation for your team.
You will learn how to use AI assistants and autonomous coding agents in a targeted manner: From intelligent requirements analysis and automated architecture design to autonomous development agents that implement complex features. You will always remain in control and understand where human expertise is indispensable.
After the training, you will be able to assess which AI tools and approaches are suitable for your specific challenges. You will know how to gradually move from simple code completion to advanced agent-based workflows.
Agenda
- Introduction & Context
- Why generative AI is shaping the future of software development
- AI concepts: tokens, autoregression, temperature, prompts, context, tools, model context protocol, memory
- Agents vs. assistants
- Introduction to agentic work
- Requirements
- AI-assisted creation, analysis, and refinement of requirements
- Automatically translate customer needs into structured requirements
- Generate epics and user stories from natural language and multimodal content
- Uniformly structured requirements with few-shot prompts
- Creating prototypes with agents without a technical background
- Architecture
- Designing system architectures with the help of AI agents
- AI-assisted decision-making and documentation
- Determining quality requirements from requirements and stakeholder interviews
- Detect contradictions in architecture with AI agents
- Identify and document technical debt with AI
- Identify deviations from the ubiquitous language with AI
- Implementation
- Increase efficiency from code completion to AI-driven implementation of complete features
- Context engineering to expand the range of tasks that can be implemented by AI agents
- Vibe coding vs. writing productive code with AI agents
- Connecting documentation and developer tools via MCP
- Creating fine-grained, explanatory commits with AI agents
- Support for API integration and library usage
- Test-driven agentic development
- Increasing code quality through refactoring and uniform concepts
- Understanding and modernizing legacy code faster
- Multi-agent workflows for further efficiency gains
- Testing & quality assurance
- Retrospective development of a test suite using AI agents
- Generate automated tests: unit, integration, and end-to-end
- Creating synthetic test data and identifying edge cases
- AI-supported reviews of code quality, security, and compliance with requirements
- Use of autonomous AI agents to improve quality
- CI/CD
- Generating CI/CD pipelines using AI agents
- Automated creation of release notes and changelogs
- Generation of infrastructure as code with AI agents
- Integration of AI-generated scripts into pipelines
- Setting up self-healing pipelines and automated troubleshooting using AI
- Operation & Monitoring
- Prioritization and assessment of alerts
- Automated bug fixing and ticket management
- Accelerating incident management through AI-based root cause analysis
- Integration of AI agents with observability stacks
- Formulating queries in observability tools
- Setting up dashboards and metrics with AI agents
Your Trainers
André Deuerling
INNOQ
Self-Contained Systems, Data Mesh, Domain-driven Design
- Agentic Software Engineering
André Deuerling is Senior Consultant at INNOQ in Germany. He is a software engineer with expertise in C++, self-contained systems and a passion for building high-performance software systems. His interests include data mesh, domain-driven design and building right-sized applications.
Torben Keller
INNOQ
- Agentic Software Engineering
Torben Keller specializes in how development teams build software with AI agents. His focus: the transition from traditional coding to Agentic Software Engineering, where developers orchestrate multiple AI agents that handle autonomous tasks. With experience from startup environments and enterprise projects, Torben helps organizations introduce AI-augmented development practices and enables teams to achieve significant productivity improvements while maintaining or improving quality and control. His work addresses the critical question facing software teams today: not whether to adopt Agentic Engineering effectively, but how to do so before the productivity gap becomes insurmountable. He is also a trainer for our Agentic Software Engineering Training (3-day) and as a speaker at conferences and meetups, he shares practical experiences and strategies for introducing agentic development approaches.