AI Joins the Team I
Combined Session
Wednesday, June 05, 2024 11:00—12:00
Location: A 03-04
Wednesday, June 05, 2024 11:00—12:00
Location: A 03-04
Have you ever wanted to control a powerful AI?
Now you can, with prompt engineering!
Prompt engineering is the art of using specific instructions, or prompts, to tell large language models (LLMs) what you want them to do. By carefully crafting prompts, you can direct LLMs to produce specific results, such as writing a poem, translating a document, or answering a complex question.
In this talk, I will give you a behind-the-scenes look at how prompt engineering works. I will show you how to create effective prompts, and I will share some amazing examples of what can be achieved with prompt engineering.
Generative AI is transforming industries. To realize its full potential, you need a modern data strategy. Join this session to learn how to develop an effective data strategy and build generative AI applications that deliver domain-specific experiences.
We'll discuss data-centric architectural patterns that can help you accelerate your AI development, improve customer experience, and gain better business insights. We will also discover how to align your data and generative AI strategy with your organization's goals and values. Through real-world examples and case studies, we'll demonstrate how organizations have successfully implemented data strategies for generative AI applications, and the significant impact it had on their business outcomes.
By the end of this session, you'll have the knowledge and tools needed to develop and implement an effective data strategy and drive your generative AI initiatives forward. You'll also have a deeper understanding how to build, deploy, and scale generative AI applications that transform your business and customer experiences.
Log data of all kinds store a wealth of information about benign and malicious identity and system behavior that are difficult for humans to understand. With examples drawn from AWS CloudTrail data, we will show practitioners how to leverage Large Language Models to mine log data and provide easily understandable, human-readable summaries of normal user session behavior as well as explain malicious activities.
