AI Automation for Controlling and Finance

Module 1: AI basics, RAG and LLM applications (2 days, live online)

• Introduction to Large Language Models (LLMs) – with a focus on real-world case studies from finance, controlling, and risk management.
• From the basics to practical application:
  • What is a prompt?
  • How does prompt engineering work?
  • How do these develop into manageable AI workflows?
• Step-by-step implementation of modern RAG workflows (Retrieval Augmented Generation) for the financial sector:
  • Document upload,
  • automated chunking,
  • Embedding,
  • Vector search and semantic search within your own data.
• Practical application with invoice PDFs, contracts or other financial documents.
• Introduction and use of no-code tools such as LangFlow for fast, visual process automation.
• Visualization and Comparison: No-Code Flows vs. Python Code – explained in a way that’s easy to understand and practical for everyone.
• Understanding how to apply AI-supported document analysis and Q&A systems to your own data.
• Group and individual exercises: From the initial idea to a functioning AI solution in your own context.
• Workshop: Application and practice session featuring realistic examples from finance and controlling, as well as participants' own questions.
• Immediate application: After completing the module, you will be able to identify suitable processes and develop your first concrete AI use cases.

Goal: You will not only understand the technology, but also build your own AI-powered workflows and develop your first practical applications for your work environment.

Module 2: AI automation & no-code/Python integration (1 day, presence)

• Hands-on with AI tools for finance, controlling & accounting:
  • Development of custom reporting and accounting tools (e.g., for double-entry bookkeeping, automated reports).
  • Reporting workflows using SQL agents, charting agents, and writing agents (e.g., automatically generated reports with charts).
  • Automation of typical analysis and evaluation processes in the finance sector—visually using LangFlow and through the integration of pre-built Python components.
• Combining no-code and Python: Even non-programmers can contribute—technical components are integrated step by step with guidance.
• Live Demo: Integrating Python nodes into LangFlow for advanced logic.
• Application in Day-to-Day Business Operations: Typical Finance Automation Projects and Their Structured Implementation.
• Automation framework (deepening & application):
  • Advanced exercises: Selecting and outlining specific automation projects that can be implemented using AI workflows.
  • “From Idea to Proof of Concept” – Developing a Custom Roadmap for Implementation in a Corporate Context.

Goal: You will develop your own automations, combine no-code and assisted-code building blocks, and be able to optimize financial processes in a structured, AI-driven manner.

Module 3: AI Systems & Integration in a Finance Context (1 day, in-person)

• Overview: What are AI agents, and how can they be effectively utilized in finance and controlling processes?
• From individual workflows to a system: How multiple components (e.g., data, models, and AI logic) are integrated into a seamless AI-powered process.
• Practical Application: Expanding existing AI workflows into integrated applications.
• Introduction to fundamental architectural concepts using LangGraph and Python: How to structure and manage AI workflows.
• Application: Integration of external data sources (API), databases, and simple user interfaces (e.g., Streamlit).
• Code-assisted work: You’ll work with pre-made templates and learn how to use AI to customize and expand them as needed.
• Use cases from the MediTech AG story, e.g.:
  • Development of an integrated AI system featuring a user interface (Streamlit), AI logic, and database connectivity.
  • Building hybrid AI workflows using on-premises models (e.g., Ollama) and cloud solutions.
  • Development of an AI-based benchmarking approach to support management decisions.

Some of the use cases build on one another and demonstrate how individual applications gradually come together to form an integrated system.

• Automation Framework (Transfer): Structured planning of a company's own AI system.

Objective: You will understand how individual AI applications are combined to form integrated systems, and you will be able to design and develop simple solutions in a structured manner.

Module 4: Practical transfer & automation framework (self-learning phase)

• Direct transfer to corporate reality:
  • Analysis and selection of automation potential in your own company using a structured AI automation framework.
  • Step-by-step: Identification, evaluation, prioritization and conception of your own AI automation project.
  • Development of an individual AI use case including business benefits, resource estimation and implementation outline (functional & technical).
  • Application of the framework for concrete planning of the technical implementation, including interfaces, data preparation, integration of LLMs, machine learning and automation tools.

Goal: You develop an implementable automation concept that can create immediate value in your company.

Module 5: Presentation & optimization of your own AI projects (1 day, live online)

• Presentation of your individual use cases:
  • Presentation of your project, including cost-benefit analysis, workflow, technical and organizational implementation.
  • Peer and trainer feedback: discussion and fine-tuning with the group.
  • Joint sharpening of practical projects for maximum company benefit.
  • Implementation recommendations and next steps for implementation in everyday working life.

Goal: You will receive valuable feedback, strengthen your implementation skills and complete the program with a sustainable automation project that delivers real added value for your company.