Top 20 AWS re:Invent 2024 breakout sessions to stay on top of everything related to generative AI

Generative AI continues to transform industries, making it crucial for businesses to stay updated on the latest advancements and best practices. Deploying Generative AI in production presents unique challenges due to the distinct architecture it requires compared to traditional MLOps. Here are the top AWS re:Invent 2024 sessions to help you navigate the rapidly evolving landscape of generative models. This is an expanded version of my guide which is featured on AWS Re:Invent 2024 website.

This year, re:Invent offers both in-person and virtual experiences. You can register for virtual attendance for free through the AWS Portal, providing access to keynotes, leadership insights, and breakout sessions. The sessions listed below are available in person and online on the re:Invent platform, organized into the following themes:

Basics

These sessions lay the groundwork for understanding and effectively utilizing generative AI technologies. They will cover foundational concepts, focusing on prompt engineering and key decision-making factors for leaders.

Use Cases

An important part of designing great architecture for LLM is understanding success stories for implementing them. Real-world applications of generative AI, demonstrating how businesses across various industries are harnessing this technology to drive innovation and efficiency.

Amazon Q

Amazon Q is a generative AI-powered assistant designed to enhance productivity across various business functions. Sessions in this category explore Amazon Q’s capabilities in revolutionizing business intelligence, employee productivity, and developer efficiency.

Data for Generative AI

Data is the foundation of any AI model, especially Generative AI. High-quality, well-structured data directly influences the accuracy, efficiency, and relevance of AI applications. These sessions focus on strategies for building a robust data foundation, handling data governance, and optimizing data architectures, which are essential for customizing and deploying AI models effectively.

LLMOps

These sessions address the operational challenges and best practices for deploying and maintaining large language models (LLMs) in production environments. These sessions focus on the infrastructure, scalability, and cost-effectiveness required to successfully integrate LLMs into business workflows.

Basics

[TNC101] Introduction to prompt engineering

This session provides a comprehensive introduction to prompt engineering, essential for leveraging generative AI models effectively. Attendees will learn foundational concepts of prompt engineering, including different prompting techniques like zero-shot, few-shot, and chain-of-thought prompting, making it ideal for those new to the field.

[TNC102] Generative AI for decision-makers

Designed for leaders, this session covers the critical factors that influence decision-making in generative AI projects. It offers insights into the benefits, risks, and strategic considerations necessary to build a generative AI–ready organization, making it a must-attend for those overseeing AI initiatives.

[AIM306] Prompt engineering best practices for LLMs in Amazon Bedrock

This session delves into advanced prompt engineering techniques for optimizing LLM outputs, with a focus on the Anthropic Claude 3 model. Attendees will explore how to integrate prompt engineering into system architectures and use API parameters for model tuning, providing valuable knowledge for enhancing AI solutions.

[DEV301] The art of transforming foundation models into domain experts

Learn how to customize foundation models to specialize in specific domains. This session covers fine-tuning techniques, Retrieval Augmented Generation, and transactional agents, offering practical demonstrations that equip attendees with the tools to build domain-specific AI applications.

Use Cases

[NTA301] Automating scalable order processing using generative AI

Learn how AffinityX automated their order processing workflow using generative AI, achieving scalability and cost savings. This session provides valuable insights into applying AI to streamline business processes, making it relevant for companies facing similar challenges.

[RCG202] Neiman Marcus revolutionizes the luxury experience with generative AI

Learn how Neiman Marcus uses generative AI to create personalized customer experiences, driving engagement and business growth. This session is essential for retail professionals interested in using AI to enhance customer interactions and loyalty.

[BIZ201] Securing generative AI and LLM interactions with AWS Wickr

Discover how AWS Wickr can help secure generative AI interactions, ensuring compliance and governance in AI workloads. This session is critical for organizations that prioritize security and privacy in their AI initiatives, offering practical solutions for managing AI-related risks.

[MFG201] Empowering the next-generation industrial operator with generative AI

Learn how Georgia-Pacific uses generative AI to support industrial operators in troubleshooting and decision-making. This session is valuable for manufacturers looking to enhance workforce productivity and reduce downtime through AI-powered tools.

[AES305] How ICEYE uses satellite data & generative AI to speed flood response

Explore how ICEYE leverages generative AI to improve flood response efforts by processing satellite data in real time. This session highlights the critical role of AI in disaster management, offering lessons for organizations involved in emergency response and climate change mitigation.

Amazon Q

[BSI101] Amazon Q in QuickSight: Revolutionize data insights with Generative BI

Discover how Amazon Q in QuickSight empowers organizations to create interactive data insights quickly. This session showcases the potential of Generative BI in transforming data analysis and decision-making, featuring real-world examples from AWS customers who have eliminated manual reporting bottlenecks.

[AIM101] Boost employee productivity with Amazon Q Business

This session explores Amazon Q Business’s capabilities in enhancing productivity through generative AI-powered assistants. Attendees will learn how to implement secure, privacy-compliant AI solutions that automate tasks and provide valuable summaries, making it an essential session for organizations looking to leverage AI across various use cases.

[AIM201] Maximize Amazon Q Business impact with Amazon Q Apps

Learn how Amazon Q Apps enables employees to create custom generative AI-powered applications. This session provides insights into how these apps can streamline tasks and enhance productivity, built securely on enterprise knowledge bases.

[DOP204] Amazon Q Developer: Your gen AI assistant for software development

Developers can discover how Amazon Q Developer accelerates software development processes by automating tasks and enhancing experimentation. This session highlights how generative AI tools can support the entire software lifecycle, from design to optimization, making it invaluable for development teams.

Data for Generative AI

[STG201] Build a data foundation to fuel generative AI

Data is a key differentiator in generative AI applications, and this session covers essential strategies for building a strong data foundation. Attendees will learn how to align their data strategies with AI goals, ensuring that their generative AI solutions are both relevant and effective.

[DAT319] A practitioner’s guide to data for generative AI

This session offers practical guidance on deploying generative AI applications with a focus on Retrieval Augmented Generation (RAG). It’s designed for data practitioners who want to implement best practices in data architecture, processing, and governance to optimize AI applications.

[DAT405] Deep dive into Amazon Aurora and its innovations

Delve into the latest features of Amazon Aurora, including its capabilities for supporting generative AI applications. This session is essential for database professionals who want to understand how Aurora can optimize the storage and retrieval of vector embeddings and other AI-related data.

LLMOps

[SVS319] Unlock the power of generative AI with AWS Serverless

This session covers how to build scalable, cost-effective generative AI applications using AWS Serverless technologies. It’s essential for anyone looking to implement secure, high-performance AI workflows, with practical insights into real-world use cases and architectural patterns.

[AIM203] Accelerate gen AI application development with Amazon Bedrock Studio

Learn how Amazon Bedrock Studio simplifies the development of generative AI applications. This session provides a hands-on overview of how to use Bedrock Studio for rapid prototyping and deployment, abstracting away infrastructure complexities for developers.

[AIM307] Reduce FM deployment costs and latency with Amazon SageMaker

This session focuses on optimizing the deployment of foundation models using Amazon SageMaker. Attendees will gain insights into cost-effective strategies for large-scale AI inferencing, making it crucial for organizations looking to scale their AI operations efficiently.

[AIM303] Customize FMs with advanced techniques using Amazon SageMaker

Explore advanced customization techniques for foundation models using Amazon SageMaker. This session is vital for data scientists and ML engineers aiming to tailor models to specific needs while ensuring responsible AI practices and enhancing transparency.

Get Rustem Feyzkhanov’s stories in your inbox

Join Medium for free to get updates from this writer.

Remember me for faster sign in

This guide should help you navigate the key Generative AI sessions at re:Invent 2024, tailored to your interests and business needs. Whether you’re a decision-maker, developer, or industry professional, these sessions will provide valuable insights into how to leverage generative AI in your organization effectively.