AWS Discovery Day - Introduction to Promt Engineering (Webinar)

In this webinar, you will learn how to create and optimize prompts for a variety of generative AI models. First, this course covers the basics of foundation models, including a subset of foundation models (FMs), called large language models (LLMs). Then, the course covers the fundamental concepts of prompt engineering, such as the different elements of a prompt and some general best practices for using prompts effectively. Finally, the course provides information about basic prompt techniques, including zero-shot, few-shot, and chain-of-thought (CoT) prompting.

Dato og tidspunkt:

11.september: 12:30-13:30

Activities

This course includes lecture materials, visual presentation, and audience participation.

•    Level: Fundamental
•    Duration: 60 minutes

Learning objectives

•    Identify the fundamental concepts of FMs and LLMs
•    Define prompt engineering and identify the best practices for designing effective prompts
•    Identify the basic types of prompt techniques, including zero-shot, few-shot, and CoT  techniques

Intended audience

•    Prompt engineers
•    Data scientists
•    Developers

Event outline 

Module 1: Foundation models and large language models
•    How does a foundation model function?
•    Training FMs
•    Types of FMs
•    Large language models
•    Transformer architecture
•    Neural networks
•    LLM use cases

Module 2: Key concepts of prompt engineering
•    Fine-tuning and prompt engineering
•    Elements of a prompt
•    Best practices for designing effective prompts
•    Practice with prompts

Module 3: Basic prompt techniques
•    Zero-shot prompting
•    Few-shot prompting
•    Chain-of-thought prompting

Conclusion

 

What is AWS Discovery Days?


AWS Discovery Days, hosted by official AWS Training Partners, introduce cloud concepts, including generative AI, security, machine learning, migrations, and modern data strategy. Expert AWS Instructors will help you learn what’s possible in the cloud and how to achieve it with AWS.