Seminar Structured Prompt Engineering
In-person events in Wiesbaden or online seminar (duration: 1 day): €890 per person (net)
The seminar is not only aimed at professionals in the fields of data analysis, AI development and programming who want to deepen their skills in prompt engineering
Dates for Open Training - Crash Course: 20.02.2025, 03.04.2025, 11.09.2025
LEARNING OBJECTIVES AND AGENDA
Goals:
Teaching basic and advanced prompt engineering techniques.
Learn how to effectively test prompts with the langfuse backend.
Development and application of systematic test methods for evaluating prompt quality .
Practical application of zero-shot , one-shot and few-shot techniques.
Promoting individual skills through practical exercises and group discussions.
IN-HOUSE SEMINAR
Seminars held at the customer's location
€1,390.00
per day up to 4 participants plus statutory VAT
All content of the in-house seminars is individually tailored and taught to specific target groups .
Intensive follow-up support enables participants to implement their knowledge in the shortest possible time.
Recommended seminar duration: 1 day
Rental fees for training notebook (on request): 60,- Euro (per day, per training computer)
WORKSHOP
You tell us your topics!
Price on request
plus statutory VAT and travel expenses if applicable
All workshop content is individually tailored and taught to specific target groups .
We are happy to conduct the workshop at your location, in Wiesbaden or online.
Rental fees for training notebook (on request): 60,- Euro (per day, per training computer)
Unit 1: Basics of Prompt Engineering
Introduction to the principles of prompt engineering.
Hands-on session on creating and analyzing prompts.
Using Llama Index and Langchain for prompt development.
Discussion of the components of a prompt: context, system, user, etc.
Unit 2: Effectively Developing Prompts with langfuse/langgraph
Basics of the langfuse/langgraph system.
Creating test data and specific prompts for quality assurance.
Calculating and analyzing metrics to evaluate the prompts.
Strategies for effective prompt development and versioning.
Unit 3: Zero-shot, One-shot and Few-shot Techniques
Introduction to the concepts of zero-shot, one-shot and few-shot techniques.
Practical application of these techniques using the langfuse backend.
Developing prompts to maximize the efficiency of these approaches.
Unit 4: Advanced Prompt Engineering Techniques
Learn advanced techniques:
ReAct (Reasoning and Action)
Chain of Thought (CoT) Prompting
Self-consistency with CoT
Tree-of-Thought (ToT) Prompting
Reasoning via Planning (RAP)
Self-refine and reflection
Language Agent Tree Search (LATS)
Practical exercises on applying these techniques in real-life scenarios.
CONTENTS
There are many tips, information, PDF documents with hints, etc., on prompt engineering that enable truly efficient prompt creation , reveal the secrets of prompt engineering , and so on. Then there are tips like, "Write in the prompt that you'll get $100 for a better answer," etc.
All of this is completely unproductive and, in practice, only results in a waste of scarce resources like time and money. Why not use a tried-and-tested approach in software development ? Create labeled datasets with data and the expected results. Since this is time-consuming, simply use a backend like langfuse or langhraph. Here, you can also version your prompts , allowing for effective and completely transparent development.
Because: In today's world of artificial intelligence (AI) and machine learning , prompt engineering is a crucial skill for maximizing the performance of large language models (LLMs) . Our one-day seminar " Effective Prompt Engineering " offers a comprehensive introduction and practical application of these techniques. Participants will learn how to use the langfuse backend to conduct systematic tests to evaluate and optimize the quality of prompts. By creating and analyzing prompts, participants will develop a deep understanding of how to design effective prompts that deliver precise results.
The seminar is not only aimed at professionals in the fields of data analysis, AI development, and programming . It offers valuable insights into advanced techniques such as zero-shot, one-shot, and few-shot learning methods , which help participants significantly increase the efficiency and accuracy of their models. Through the targeted use of techniques such as chain-of-thought (CoT) prompting and self-consistency, participants will learn strategies to effectively manage their LLMs and develop application-oriented solutions.
The course is structured into four units , each focusing on different aspects of prompt engineering . The first unit teaches the fundamentals and required concepts, while the subsequent units offer in-depth knowledge of using the langfuse/langgraph system and developing and testing prompts. Each unit includes practical exercises that allow participants to directly apply what they have learned and further develop their skills.
Attending this seminar will not only help professionals expand their knowledge of prompt engineering, but also deepen their expertise in data science and AI applications overall. Register today to learn from experienced instructors and discover the latest techniques in prompt engineering!