2024 AWS Summit Hong Kong

How Amazon.com enhanced shopping with gen AI and foundation models

Time: 11:00 - 11:30AM
Venue: Theatre 2
Level: 300 - Advanced

Amazon is one of the most popular websites in the US. Its search engine is one of the most heavily used services in the world, indexing billions of products and serving hundreds of millions of customers worldwide. In this session, learn how Amazon Search uses the robust services offered by AWS and generative AI techniques to build delightful shopping experiences for Amazon customers. See the steps taken to bring generative AI research ideas to production using AWS—from scaling scientist productivity to building foundation model refresh and inference capabilities in production using Amazon silicon.

Reinventing with generative AI on AWS

Time: 11:40AM - 12:10PM
Venue: Theatre 2
Level: 100 - Introductory

From startups to enterprises, organizations of all sizes are getting started with generative AI. They want to capitalize on this new technology and translate the momentum from betas, prototypes, and demos to real-world innovations and productivity gains. With enterprise-grade security and privacy, leading foundation models, a data-first approach, and the most performant, low-cost infrastructure, AWS is trusted to deliver generative AI-fueled innovation. In this session, learn how new generative AI services and capabilities like Amazon Bedrock and Amazon Q can help deliver business value across key use cases to enhance employee productivity, improve customer engagement, and build new, differentiated experiences.

Generative Business Intelligence (BI) in Amazon QuickSight

Time: 2:10 - 2:40PM
Venue: Theatre 2
Level: 200 – Intermediate

Building secure generative AI applications on AWS

Time: 3:30 - 4:00PM
Venue: Theatre 6
Level: 300 – Advanced

Generative AI is one of the most disruptive technologies of our generation and has the potential to revolutionize many industries. In this chalk talk, explore how to build secure generative AI applications on AWS with Amazon SageMaker and Amazon Bedrock using various AWS services and tools spread across infrastructure and network isolation, data protection, authentication and authorization, and detective controls. Also, learn generative AI reference architectures and best practices to improve the security of your ML pipeline.

Advancing ESG practices in smart buildings with AI-driven digital twins (featuring ATAL)

Time: 3:30 - 4:00PM
Venue: Theatre 3
Level: 100 – Foundational

With the increasing importance of sustainability and the development of smart cities, the integration of ESG considerations into building management has become essential. This presentation examines the use of AWS tools to empower the R&D of ATAL's AI-driven Digital Twins for enhancing ESG practices in smart buildings. Through collaboration with AWS, our reinforced big data analytics and cloud computing capabilities come together to create the AI-driven Digital Twin in enabling organisations to streamline their operations. The AWS tools provide a scalable and secure infrastructure for ATAL's AI-driven Digital Twin to manage significant amounts of data, empowering the Digital Twin to automate the entire data processing, including data collection, analytics, visualisation, and reporting, in order to facilitate efficient ESG management. ATAL's Digital Twin enables facility managers to optimise building functionalities, addressing energy efficiency, maintenance, space utilisation, and security monitoring. Property owners benefit from improved visibility into building health for portfolio valuation and risk management. The integration of AWS tools also supports the incorporation of big data analytics into measurements of indoor environmental quality (IEQ), promoting healthier workspaces and enhancing occupant comfort and well-being.

Harness the power of AWS to build game-changing applications (featuring Fano Labs)

Time: 4:40 - 5:10PM
Venue: Theatre 4
Level: 200 – Intermediate

Organizations in every industry are looking to solve bigger challenges, turn groundbreaking ideas into reality, and deliver innovative solutions at scale. This requires an infrastructure that scales limitlessly, delivers high performance at optimized costs, and supports constant innovation. In this session, learn how organizations are using the secure, innovative, and performant AWS Cloud to build game-changing applications. With the broadest and deepest functionality for compute, AWS can support the needs of even the most demanding workloads to run complex ML models, leverage generative AI, or implement applications that require large-scale high performance computational power at low costs.

Unlock generative AI potential in retail and ecommerce (featuring CASETiFY)

Time: 1:30 - 2:00PM
Venue: Theatre 4
Level: 200 – Intermediate

Use RAG to improve responses in generative AI applications & Transform student learning experience with LLM on AWS (featuring Goodnotes)

Time: 2:10 - 2:40PM
Venue: Theatre 3
Level: 300 – Advanced

Your generative AI applications can deliver better responses by incorporating organization-specific data through a technique known as Retrieval Augmented Generation (RAG). However, implementing RAG requires time to configure connections to data sources, manage data ingestion workflows, and write custom code to manage the interactions between the foundation model (FM) and the data sources. Join this session to learn how to make the process much easier using Amazon Bedrock. Based on the user prompt, Amazon Bedrock automatically identifies data sources, retrieves the relevant information, and adds the information to the prompt, thereby giving the FM more information to generate responses. See how it works in this session.

Goodnotes iPad app of the year 2022 is empowering 19M+ users globally to transform their productivity and learning experience using AI on AWS. In this session, you'll learn how Goodnotes develop AI on AWS, and the technical best practice to consume LLM at scale with
cost effectiveness on AWS.

Supercharge your development with AWS generative AI developer tools

Time: 3:30 - 4:00PM
Venue: AWS Dev Day (S424)
Level: 300 – Advanced

Generative AI has the power to help you reimagine the way that developers and organizations learn, plan, create, deploy, and securely manage applications. Across the software development lifecycle—from architecting to developing, testing, deploying, and maintaining applications—generative AI developer tools save time, automate undifferentiated heavy lifting, and create space for innovation and creativity. Learn how AWS is innovating responsibly to deliver tools such as Amazon Q and Amazon CodeWhisperer so that builders can focus on meaningful work that drives impact for their customers.

Navigating the future of AI: Deploying generative models on Amazon EKS (featuring Dayta AI)

Time: 3:30 - 4:00PM
Venue: Theatre 5
Level: 300 – Advanced

Model choice in Amazon Bedrock

Time: 3:30 - 4:00PM
Venue: AWS Training and Certification Upskill Centre (S421)
Level: 200 – Intermediate

Amazon Bedrock helps you rapidly adapt and take advantage of the latest generative AI innovations with easy access to a choice of high-performing FMs from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon. In this session, learn about how to experiment, evaluate, and build with the best FMs for your use case using Amazon Bedrock.

Drive personalized CX using generative AI and Amazon Personalize

Time: 4:05 - 4:35PM
Venue: AWS Dev Day (S424)
Level: 200 – Intermediate

Delivering the best experience is critical to capture and retain customers today. With generative AI, it is possible to hyper-personalize targeted recommendations for shopping and streaming. While standard taglines like “People who bought this also bought . . .” or “Because you watched . . .” entice some, they don’t fully address individual interests. Companies must find ways to dynamically generate compelling, highly customized content. Amazon Personalize delivers capabilities powered by ML and generative AI to help brands create meaningful experiences. Join this session to hear from powerhouse AWS media customer FOX and learn how hyper-personalized experiences can be used to build engagement and drive revenue.

New AWS generative AI features and tools for developers

Time: 4:05 - 4:35PM
Venue: AWS Training and Certification Upskill Centre (S421)
Level: 200 – Intermediate

Explore how generative AI coding tools are changing the way developers and companies build software. Generative AI–powered tools are boosting developer and business productivity by automating tasks, improving communication and collaboration, and providing insights that can inform better decision-making. In this session, see the newest AWS tools and features that make it easier for builders to solve problems with minimal technical expertise and that help technical teams boost productivity. Walk through how organizations like FINRA are exploring generative AI and beginning their journey using these tools to accelerate their pace of innovation.

Customize FMs for generative AI applications with Amazon Bedrock

Time: 4:40 - 5:10PM
Venue: Theatre 3
Level: 300 – Advanced

Foundation models (FMs), like LLMs, have shown impressive capabilities across many natural language tasks. However, directly utilizing these models for applications can present challenges. In this session, explore and compare methods for effectively adapting foundation models for your applications. Learn how to evaluate prompt engineering, which reformulates the task into natural language, and fine-tuning, which updates the models' parameters on new tasks and use cases. Explore the trade-offs between usability and resource requirements for each method. Learn how to productively use the capabilities of large models, and discover future improvements to their adaptability.

Simplify generative AI app development with Agents for Amazon Bedrock

Time: 4:40 - 5:10PM
Venue: AWS Dev Day (S424)
Level: 300 – Advanced

FMs effectively conduct conversations, create content, and drive productivity, but they can deliver more value if they’re equipped to transact with company systems to complete multistep tasks. Fully managed Agents for Amazon Bedrock enables generative AI applications to help perform multistep tasks using enterprise systems and data sources, saving you from engineering prompts, managing session context, or manually connecting systems. In this session, deep dive into how to build agents using Amazon Bedrock.

Automate app upgrades & maintenance using Amazon Q Code Transformation

Time: 4:40 - 5:10PM
Venue: AWS Training and Certification Upskill Centre (S421)
Level: 200 – Intermediate

Developers spend significant time completing the undifferentiated work of maintaining and upgrading legacy applications. Teams need to balance investments in building new features with mandatory patching and update work. Now, using the power of generative AI, Amazon Q can expedite these critical upgrade tasks, transforming applications to use the latest language features and versions. Join the session to learn how your team can automate Java application upgrades and soon port .NET framework applications to cross-platform .NET.

Build a data foundation to fuel generative AI (featuring Lalamove)

Time: 3:30 - 4:00PM
Venue: Theatre 4
Level: 200 – Intermediate

Data has long been considered a strategic asset by organizations, but generative AI puts a renewed emphasis on the importance of a data strategy. Whether you are building your own model or customizing a foundation model, your data is a key differentiator for generative AI, so you need a data strategy that supports relevant, high-quality data. In this session, learn about the data tools that can fuel your generative AI strategy and the common data patterns required to transform your generative AI application from a generic tool to a program that truly knows your business and your customer.

AWS vector database capabilities with best practices for querying vector data

Time: 4:40 - 5:10PM
Venue: Theatre 6
Level: 200 – Intermediate

Innovation on vector database capabilities have rapidly evolved. In this session, we will share the latest in vector database capabilities across the AWS portfolio. We will then focus on best practices for vector search using Aurora PostgreSQL and RDS for PostgreSQL so you can deliver a high-performance experience to your customers. You will also learn how to store data from Amazon Bedrock in an Amazon Aurora PostgreSQL-Compatible Edition database and learn what SQL queries and tuning parameters optimize the performance of your application when working with AI/ML data, vector data types, exact and approximate nearest neighbor search algorithms, and vector-optimized indexing.

Panel Discussion: Advancing responsible AI in the generative era (featuring HKSTP & Hong Kong Computer Society)

Time: 2:10 - 2:40PM
Venue: Theatre 5
Level: 100 – Foundational

The rapid growth of generative AI brings promising innovation and at the same time raises new challenges around safe and responsible development and use. Some of these challenges, such as bias prevention and explainability, were common before generative AI, while some, including hallucination, toxicity, and intellectual property protection, are unique to generative models. In this session, learn about the challenges presented by generative AI, discuss best practices for building responsibly, and explore new hands-on AWS tools for responsible AI usage.

Securely build generative AI apps and control data with Amazon Bedrock

Time: 4:05 - 4:35PM
Venue: Theatre 6
Level: 300 – Advanced

Generative AI applications have captured widespread attention; however, they have also introduced new security challenges, especially around the handling of customer data. Organizations want to ensure that their data remains safe and secure while working with foundation models (FMs) and don’t want to worry about their data being used to train an FM. Amazon Bedrock provides comprehensive data protection and privacy. In this chalk talk, explore architectures, data flows, and security-related aspects of model fine-tuning, as well as prompting and inference, while you learn about Amazon Bedrock’s security capabilities.

Build responsible AI applications with Guardrails for Amazon Bedrock

Time: 4:40 - 5:10PM
Venue: Theatre 1
Level: 200 – Intermediate

Guardrails for Amazon Bedrock help organizations manage end-user experiences based on their application-specific requirements and responsible AI policies. You can deliver consistently safe user experiences through generative AI applications, no matter the underlying FM. Learn how this new capability gives you the ability to define custom policies and manage interactions between users and foundation models (FMs) by filtering out disallowed topics and harmful content. Finally, see demos on how to create and apply custom tailored guardrails with FMs and Agents for Amazon Bedrock to implement responsible AI policies within your generative AI applications.