Agentic Software Engineering Training

Generative AI is changing how we build software — from single code snippets to entire agent-driven development workflows. In our new three-day training course, Agentic Software Engineering, you’ll learn how to turn this transformation into actionable practices for your team.

Focus: Agentic Engineering

You’ll learn how to effectively use AI assistants and autonomous agents — from smart requirements analysis and automated architecture design to coding agents that independently implement complex features. Throughout the process, you stay in control and know where human expertise remains critical.

What’s in it for you

After the training, you’ll be able to assess which AI tools and approaches make sense for your specific challenges. You’ll know how to move from basic code completion to advanced, agent-based workflows — step by step.

Who is this for?

This training is designed for developers, architects, and tech-adjacent roles who want a systematic, hands-on approach to using generative AI across the entire software development lifecycle.

Agenda

1. 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
2. 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
   • Create prototypes with agents without technical background
3. Architecture
   • Design system architectures using AI agents
   • AI-supported decision-making and documentation
   • Derive quality requirements from requirements and stakeholder interviews
   • Uncover contradictions in architecture with AI agents
   • Identify and document technical debt with AI
   • Identify deviations from ubiquitous language with AI
4. Implementation
   • Increase efficiency from code completion to AI-driven implementation of complete features
   • Context engineering to expand the scope of tasks that AI agents can handle
   • Vibe coding vs. writing production code with AI agents
   • Integration of documentation and developer tools via MCP
   • Create fine-grained, explanatory commits with AI agents
   • Support for API integration and library usage
   • Test-driven agentic development
   • Improve code quality through refactoring and consistent concepts
   • Understand and modernize legacy code faster
   • Multi-agent workflows for further efficiency gains
5. Testing & Quality Assurance
   • Retroactive construction of test suites using AI agents
   • Generate automated tests: unit, integration, and end-to-end
   • Create synthetic test data and identify edge cases
   • AI-supported reviews for code quality, security, and requirement fulfillment
   • Deploy autonomous AI agents to improve quality
6. CI/CD
   • Generate 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
   • Set up self-healing pipelines and automated error resolution using AI
7. Operations & Monitoring
   • Prioritization and assessment of alerts
   • Automated bug fixing and ticket management
   • Accelerate incident management through AI-based root cause analysis
   • Integration of AI agents with observability stacks
   • Formulation of queries in observability tools
   • Set up dashboards and metrics with AI agents

If you have any questions about Agentic Software Engineering or our services, feel free to reach out to Robert Glaser, Head of Data & AI at INNOQ.