Course Overview
As generative AI becomes more common, the ability to interact with large language models is shifting from niche knowledge to a necessary skill across many different industries and roles. In this course, you will learn the fundamentals of prompting large language models and exploring further techniques for improving the output from large language models. You will also explore similar concepts when working with multimodal models such as Gemini Vision Pro.
Prerequisites
There are no prerequisites for this course. The workshop aims to provide both introductory and advanced insights into Gen AI, making it suitable for individuals with varying levels of AI expertise.
Course Objectives
- Understand the basics of generative AI and how it compares to traditional AI.
- Design effective prompts following general best practices.
- Improve large language model outputs using easy-to-approach prompt engineering techniques.
- Write effective prompts for interacting with multimodal models such as Gemini Vision Pro.
Outline: Writing Effective Prompts for Generative AI (WEPGAI)
Module 1 - Understanding Generative AI
Topics:
- Gen AI vs. AI/ML
- Gen AI Applications
- Business Impact of Gen AI
Objectives:
- Define generative AI as a subset of AI.
- Discuss the potential impact of AI on organizations .
- Provide examples of generative AI applications.
Module 2 - Prompt Design
Topics:
- Prompt content types.
- Prompt design strategies.
- Iterating prompts for improvement.
Objectives:
- Understand the role of context and examples in prompts.
- Iterate on prompts to improve model output.
Activities:
- Lab: Introduction to Prompt Design
Module 3 - Improving Prompts
Topics:
- Prompt design versus prompt engineering
- Zero-shot and few-shot prompting
- Chain-of-thought prompting
- Overview of additional techniques
Objectives:
- Describe the difference between prompt design and prompt engineering.
- Write prompts using few-shot and chain-of-thought techniques.
- Learn about additional prompt engineering techniques being used today.
Activities:
- Lab: Improving your Prompts
Module 4 - Working with Multimodal Models
Topics:
- What is a multimodal model?
- Prompt design strategies
- Best practices for multimodal prompts
- Troubleshooting your multimodal prompt
Objectives:
- Understand the multimodal models and their use cases.
- Design effective prompts for multimodal models.
Activities:
- Lab: Writing Prompts for Gemini Pro Vision