Programmatic AI agent systems with Claude Code and LangChain
Understanding, implementing, and operating agent architectures—beyond low-code
For support, there is a technical preparation session before the first content-related webinar.
During this appointment, we will work together to:
- Claude Code installed
- checked the development environment
- A first test agent executed
The following requirements must be met in order to participate in this course:
- Computer with administrator rights to install software locally
- Option to install Claude Code (CLI) locally
- Create and configure your own Claude account (API access)
- Interest in programming and/or Python
- Willingness to complete the technical setup before the course begins
- Building understanding: Agent ≠ Workflow
- Why code is becoming necessary for agents
- Introduction to Claude Code and Vibe Coding
- Overview of LangChain and basic agentic building blocks
Setup, Vibe Coding, and first code agent
- Installation and configuration of Claude Code
- Python project structure for agents
- Vibe Coding: Developing agents together with AI
- First simple LangChain agent
- Exercise: Building a first single agent in Python
Agents with tools and memory
- Tools as Python functions
- Memory and state logic
- Differences between Tool-Use and State in n8n
- Exercise: Extending the agent with tool use and context
- Role-based agents
- Communication between agents
- delegation of tasks
- Live coding: Collaboration between multiple agents
Implement your own agent architecture
- Planner—Execute Architecture
- supervisor agents
- Coordination and condition management
- Exercise: Building a simple multi-agent system
Quality, testing, and operation
- Error handling and termination criteria
- Tests, logging, and simple monitoring approaches
- Operation of agentic systems in a corporate context
- Human-in-the-loop in the code
- Exercise: Deliberately let the agent fail and stabilize them
- Presentation of your own code agents
- Architecture comparison: Code vs. n8n
- Best practices for productive use
- Transfer to the business context
Contents and course schedule
1. From low-code to code: Why programmatic agents are necessary
- Limitations of workflow-based agents
- Why code becomes necessary for control, extensibility, operation, and agent-to-agent communication
- Agents as software architectures
2. Introduction to Claude Code, Vibe Coding, and Python
- Claude Code as coding agent and pair programmer
- Vibe Coding: Developing agents together with AI
- Basic structure of agentic Python projects
3. Implement single agents programmatically with LangChain
- LLM, prompt, tool, and memory as building blocks
- Single-agent architectures in code
- Comparison: the same agent in n8n vs. Python
4. Agent-to-agent communication and role agents
- Planner–executor architecture
- Role and supervisor agents
- Human-in-the-loop at the code level
5. Structured multi-agent architectures
- Planner–executor architecture
- Supervisor agents for coordinating agent teams
- Differentiation from simple decision agents
6. Stable operation of agentic systems
- Error handling, termination criteria, and guardrails
- Logging, testing, and traceability
- Human-in-the-loop at the code level
7. Develop and evaluate your own multi-agent systems
- Implementation of a proprietary agent system
- Reflecting on architecture and design decisions
- Transfer to real business environments
This is how you learn in this course
This course offers you a digital blended concept that has been developed for part-time learning. Thanks to a flexible mix of online seminars and self-study phases, you are sure to reach your goal. This is how you learn in this course:
Learning environment: In your online learning environment, you will find useful information, downloads and extra services for this training course after you have registered.
Self-study phases: Learn independently, at your own pace and whenever you want. Our courses offer you didactically high-quality learning material.
Live webinars: In regular online seminars, you will meet your trainers in person. You will receive answers to your questions, specific assistance and instructions on how to deepen your knowledge and apply the skills you have acquired in practical exercises.
Learning community: A digital learning community is available to you throughout the course. Exchange ideas with other participants and the trainers and ask questions.
Future Jobs Club: Get exclusive access to a business network, news, and future work hacks.
Certificate of completion and Open Badge: As a graduate of the course, you will receive a certificate of completion and an Open Badge, which you can easily share on professional networks (including LinkedIn).
Your benefit
- Youunderstand why genuine agent-to-agent systems must be implemented programmatically.
- Youdevelop AI agents with Python, LangChain, and Claude Code.
- Youimplement coordinated teams of agents with clear roles and responsibilities.
- You are proficient incentral agent architectures such as planner-executor and supervisor models.
- You know howto test, control, and operate agentic systems in a stable manner.
- You candesign, evaluate, and further develop programmatic agent systems in a technically sound manner.
Technical requirements
The following requirements must be met in order to participate in this course:
- Computer with administrator rights to install software locally
- Option to install Claude Code (CLI) locally
- Create and configure your own Claude account (API access)
- Interest in programming and/or Python
- Willingness to complete the technical setup before the course begins
Important note:
For support, there is a technical preparation meeting before the first content-related webinar. During this meeting, we will work together to:
- Claude Code installed
- checked the development environment
- A first test agent executed
Tool
Recommended for
This training course is suitable for anyone who wants to understand how to safely integrate AI agents into companies and determine their ROI. You will build a bridge between operational business requirements and technological feasibility.
- Technically savvy process managers automation experts
- Product Owner & Digital Project Managers
- Software Engineers & Technical Leads
- innovation managers data professionals
- Professionals aiming for the next level of AI integration
Start dates and details
About us - The Haufe Akademie
Your optimizer, innovator and companion since 1978 -
Your professional partner for professional development and seminars, training courses and topical conferences.
Whether on site, live online or in-house - our customised solutions, our claim to the highest level of consulting expertise and training tailored to your needs simplify the acquisition of skills for the working world of the future and sustainably facilitate professional development.
A wide range of seminars, individual coaching and our flexible formats support HR managers and decision-makers in shaping the future and developing employees, in-house teams and companies.
Experience the benefits of online training from the comfort of your own home. Our online formats meet the highest quality standards and are in no way inferior to face-to-face events in terms of practical relevance. Learn together live online in interactive groups or digitally at a time of your choice.
Do you have any questions?
We are there for you Monday to Friday 8:00 a.m. - 5:00 p.m.
Questions & Answers
In our Questions & Answers (FAQ) section, you will find all the answers and the most frequently asked questions about your selected topic.
Munzinger Str. 9
79111 Freiburg
- Planning security
- Free seminar places
- Quality standards
- Planning and locations
- Funding opportunities
- Training app
- Business Solutions
