Programmatic AI agent systems with Claude Code and LangChain
Understanding, implementing, and operating agent architectures—beyond low-code
Did you know?
This course is part of the certified "AI Agent Specialist" Master Class. Whenyou enroll in the entire Master Class,you’ll save 22 percent compared to enrolling in the individual modules.
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 is necessary for control, extensibility, and operation, as well as for agent-to-agent communication.
- Agents as software architectures.
2. Introduction to Claude Code, Vibe Coding, and Python
- Claude Code as a coding agent and pair programmer.
- Vibe Coding: Developing agents in collaboration with AI.
- Basic structure of agent-based 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 teams of agents.
- Distinction from simple decision-making 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.
- Reflect on architectural and design decisions.
- Application in real-world business settings.
This is how you learn in this course
This course offers a digital blended learning approach designed for working professionals. Through a flexible combination of online seminars and self-study sessions, you’ll be sure to achieve your goals. Here’s what you’ll learn in this training program:
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 will be available to you throughoutthe course. trainers with other participants and the trainers , and ask any questions you may have.
Certificate of Completion and Open Badge:As a graduate of the class, you will receive a certificate of completion and an open badge, which you can easily share on professional networks (such as 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 & Prerequisites
This course is right for you if you want to build AI agents yourself. You'll build, test, fail, and solve problems. If you just want to see how finished agents work, this isn't the course for you.
What You'll Bring to the Table
- A basic understanding of technology and a sense of curiosity—you don’t need any programming skills, but you do need a willingness to learn how to use tools and code
- Practical experience with automation tools such as make or n8n—or the discipline to teach yourself the basics using the provided materials before the course begins
- Practical Understanding of Digital Business Processes and Data Flows
- Your own data (real or synthetic) that you can use to train and test your agents
- A desire for personal responsibility—not as a duty, but as a driving force
Technical requirements
- Computer or laptop with a current operating system (Windows, macOS, or Linux)
- A stable internet connection and a recent web browser (Chrome, Edge, or Firefox)
- Access to Web-Based Tools
In addition to the participation fee, there are additional tool costs.
- Claude Subscription for Claude Code (Pro ~20 USD/month or Max ~100 USD/month)
- Anthropic API key (additional, pay-as-you-go, approximately 20 € in usage)
- Local computer with administrator privileges and at least 8 GB of RAM
- All you need is an interest in programming; no prior knowledge is required.
Tool
Recommended for
With this training program, you’ll become the go-to person for intelligent AI agents and play an active role in shaping your company’s hybrid workforce (humans & AI). You want to understand how to build AI agents, integrate them securely into your company, and determine their ROI.
- Technically savvy process managers automation experts
- Technically Savvy Product Owners & Digital Project Managers
- innovation managers data professionals
- Technical specialists and managers seeking to take AI integration to the next level
- Customized training courses
- Direct application in practice
- Efficient use of time and resources
Mastering the future
Design, develop, and control production-ready AI agents – with the "AI Agent Specialist" master class
Start dates and details
Training is guaranteed to take placeAbout 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
