Course · Training · Workshop
Advanced Agentic Software Engineering
The advanced course for teams already working with Claude Code or Codex: navigating very large codebases and multi-repo setups agentically, agentic code reviews, test strategies, agents in CI/CD, plus architecture, performance and token-budget optimization.
This course is for teams who already use agentic coding day to day and want to take the next step. It builds on the fundamentals of agent-based development and covers the topics that actually hurt in production: How do agents navigate very large codebases and multiple repositories without losing context? How do code reviews become agentic and still reliable? Which test strategies make agent output verifiable rather than merely plausible? How do agents run inside CI/CD pipelines for PR reviews, automatic release notes and documentation? And how do you keep architecture quality, performance and token budget under control once an entire team works with agents. The course is hands-on and built around real, large projects. We work primarily with Claude Code and position alternative tools like Codex - the concepts, workflows and orchestration patterns are deliberately kept tool-agnostic. Content and focus areas are agreed with the team in advance, so the course fits exactly your level and your codebase.
What participants say
The “AI Assisted Engineering On-Boarding” course was an outstanding experience. It provided a clear, practical, and inspiring introduction to how AI can support modern engineering work. The content was well structured, easy to follow, and highly relevant to real day-to-day challenges. What stood out most was the strong balance between theory and hands-on application. The course not only explained the concepts clearly, but also showed how to use AI tools effectively and responsibly in actual engineering scenarios. It made complex topics feel accessible and immediately useful. I especially appreciated the engaging format, the high quality of the materials, and the clear expertise of the instructors. The course created a motivating learning environment and gave me valuable confidence in applying AI-assisted approaches in my work. Overall, I can highly recommend “AI Assisted Engineering On-Boarding” to anyone who wants a practical, forward-looking, and well-designed introduction to AI in engineering. It is an excellent course that delivers real value from start to finish.
Leiter IT Entwicklung Platform & Services
The AI Assisted Engineering On-Boarding course was very practical and easy to follow and awesome! I especially appreciated the hands-on approach and the focus on real use cases. It gave me a clear understanding of how to work effectively with Claude Code in a development context. After the course, I felt much more confident getting started and applying it in daily work.
Frontend Web Developer
The course fully met all my expectations and provided a smooth introduction to the subject. With the help of the instructor and the course materials, I was able to easily overcome any initial hurdles, allowing me to get started using the agents as quickly as possible.
Senior Software Engineer
I really enjoyed the lessons and learned a lot of new stuff on this course. It teaches not only fundamentals but also how to be prepared for your next challenges. The tooling that is used is very sturdy, works very well in the lab setup and is very diverse, you can pick what you like in your projects. And most importantly: I did not write any piece of code myself, the agents did everything!
Software Engineer I
Great training on agentic software development. The trainer obviously had lots of hands-on experience with the topic, there was no question that he couldn't answer. Lab environment was very well thought through and helped a lot in practicing what we learned.
Senior Software Design Engineer
Very concrete and practical training on "Agentic Software Engineering", with a good amount of theoretical background to understand what happens behind the scenes. The instructor was very knowledgeable and willing to answer the multitude of questions.”
Software Engineer I Karakun
* Voices from this or related courses.
These customers booked courses in the same topic cluster.More customers →
Content
This advanced course builds on the fundamentals of agent-based development and is aimed at teams that already use agentic coding day to day. The course consists of the following topics and, for in-house delivery, is tailored specifically to your codebase, toolchain and focus areas. We work primarily with Claude Code, position alternative tools like Codex, and deliberately keep the concepts, workflows and orchestration patterns tool-agnostic.
– From Peer Programmer to Agent Orchestration:
- Baseline check: what already works in the team and where it gets stuck
- Interactive vs. headless: agents in the terminal, in the pipeline and as sub-agents
- Multiple agents in parallel and Git worktrees for isolated, conflict-free work
- Hands-On: analyze an existing workflow and identify bottlenecks – Large-Scale Codebase Navigation:
- Context strategies for very large codebases without overfilling the window
- Agentic exploration: targeted search, sub-agents and structured codebase maps
- Working across multiple repositories and inside monorepos
- Reusable project context (CLAUDE.md, rules, conventions) for large teams
- Hands-On: have an agent navigate a large, unfamiliar multi-repo setup – Agentic Code Reviews:
- Agents as reviewers: reviewing PRs in a structured, reproducible way
- Multi-agent and adversarial reviews: verify findings independently instead of trusting blindly
- Defining quality gates and containing false positives
- Hands-On: set up an agentic review flow for real pull requests – Test Strategies with Agents:
- Making agent output verifiable: verification loops instead of “looks plausible”
- Test generation, coverage analysis and dealing with legacy code without tests
- Test-driven agentic development and suitable guardrails
- Hands-On: secure a high-risk change with an agent-supported test strategy – Agents in CI/CD:
- Headless agents in pipelines: automatic PR reviews and checks
- Generating automatic release notes and changelogs from commits and PRs
- Maintaining documentation agentically and keeping it in sync with the code
- Security, permissions and cost control for agents in the pipeline
- Hands-On: integrate an agentic CI step into a pipeline – Architecture Decisions with Agents:
- Working out and comparing design options with agents in a structured way
- Judge panels and multiple perspectives for robust decisions
- Creating and maintaining Architecture Decision Records (ADR) with agent support
- Limits: where human decision-making remains indispensable
- Hands-On: prepare and document a real architecture decision agentically – Performance and Cost Optimization (Token Budget):
- Model selection per task: using fast vs. strong models deliberately
- Context management, prompt caching and sub-agent delegation to reduce cost
- Measuring token consumption, setting budgets and making cost per task transparent
- Hands-On: optimize a workflow for cost and latency without losing quality – Multi-Agent Orchestration and Team Rollout:
- Fan-out, pipelines and deterministic orchestration of multiple agents
- Shared rules, context frameworks and MCP servers for the whole team
- Governance, security and compliance for team-wide agent use
- Hands-On: sketch a reusable agentic framework for the team
The course is deliberately tool-agnostic: we work hands-on with Claude Code and position alternative agentic tools like Codex. The concepts, workflows and orchestration patterns transfer to any tool with equivalent 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 Advanced Agentic Software Engineering
Once a team uses agentic coding day to day, the challenge shifts: the hard part is no longer building the first feature with an agent, but using agents reliably across very large codebases, multiple repositories and entire CI/CD pipelines. This course addresses exactly those topics - agentic code reviews, test strategies, architecture decisions and optimizing performance and token budget - turning individual productivity into a team-wide, verifiable practice.Further resources:
History
The first generation of agentic coding tools proved that AI can actively modify, test and run code. With the broad adoption of Claude Code, Codex and comparable tools from 2024/2025 onwards, agentic coding became standard in developers' daily work - and new questions moved to the foreground: scaling to large codebases, reliability and cost control.
The current level of maturity shifts the focus from the single interaction to orchestration: multiple agents in parallel, sub-agents for scoped tasks, agents inside CI/CD pipelines and verification loops that make agent output checkable. Advanced Agentic Software Engineering bundles these practices into a team-wide, repeatable approach.