Workshop

This workshop is a hands-on introduction to the core concepts and best practices for interacting with OpenAI models using Prompt Engineering. There is an overview of the risks of Generative AI and the layered defence-in-depth approach that can be used to mitigate them, and then an opportunity to explore some prompt engineering techniques in an AI Playground.

Target Audience

Bring your laptop along, but do not worry, you can finish the workshop at home at your own pace.

Workshop Overview

• Generative AI models can generate human like text, images, and code
• Generative AI models are stateless: they do not learn, and are constrained by their training data which is frozen at a fixed point in time
• Azure OpenAI Service is a managed service that provides access to state-of-the-art natural language generative AI models, including ChatGPT and GPT-4 from OpenAI with the security and enterprise promise of Azure.
• Azure OpenAI Service provides a simple REST API for accessing these models
• Prompt engineering is a technique for “grounding” generative AI models, and can be used to influence the style of their output, provide factual information, and constrain their behavior.

Key Takeaways

By the end of this workshop, you should be able to:

• Describe GPT model capabilities and implementation
• Understand prompt engineering concepts and best practices
• Apply prompt engineering techniques to your own generative AI solutions

Benefits for Developers, who often work on building applications, integrating AI models, or creating data pipelines. Here are two benefits:

• Improved AI Model Interaction for Faster Development
• Enhanced Data Pipeline Automation with AI-Driven Insights

Benefits for Operations Teams, responsible for managing infrastructure, ensuring system reliability, and optimizing workflows (key aspects of DevOps), can also benefit from prompt engineering skills, particularly in an AI-driven DevOps environment. Here are two benefits:

• Streamlined Incident Management with AI-Assisted Troubleshooting
• Optimized Infrastructure Management with AI-Driven Automation

Prerequisites for Participants

• Use your own laptop.
• Launch a modern browser. (Use edge or chrome for the best experience)
• GitHub username and access to the internet. They can access the workshop materials and the AI Playground for a month after the Conference.

Useful Links

1. Azure OpenAI models

Tedx Speaker, developer community mentor, Microsoftie and international conference Speaker. I live at the heart of the coding community and help drive awareness and engagement as a developer advocate