Accelerating DevOps: Leveraging AWS tooling for Automation and CI/CD (Level 300)
Many builders are facing challenges when implementing DevOps practices - from security and compliance, continuous integration, to effectively monitoring and scaling applications. In this session, learn the DevOps tools from AWS to manage the tasks, deploy at scale, and maintain your ability to deliver applications and services at high velocity. The session includes practical guidance on how you can move click ops to infrastructure as code, build a release pipeline, automate monitoring, and logging for your infrastructure and applications.

Speaker: Faraz Masood, Senior Solutions Architect, AWS
Duration: 30mins

Deploy Infrastructure as a Code on AWS (Level 200)
A new category of tools is emerging that challenges the legacy-centric approach to building modern cloud applications. In addition, the complexity of configuring services, implementing best practices, and securing workloads has led to greater pressure on builders trying to maintain productivity, cost, performance, and time to market. Join this session as we dive into Infrastructure from code, a configuration-free approach that interprets application code, automatically deploys, configures, and optimizes infrastructure to support workloads. Find out how IaC tools from AWS including AWS Cloud Formation and AWS Cloud Development Kit (AWS CDK) enables seamless integration with development workflow. This session also includes step-by-step demo to help you get started.

Speaker: Nelli Lovchikova, Solutions Architect Manager, AWS
Duration: 30mins

Observability for builders (Level 200)
Observability is a practice that provides builders and developers with better insights into application behavior, enabling earlier identification, and rectification of application defects. In this session, we outline the steps to effective implementation of observability for modern applications. We then walk through how to enhance your application observability. Discover the tools and resources so you are empowered to rapidly identify, diagnose, and remediate application issues. We demonstrate on a Java app how logs, metrics, traces work by default, without any external libraries. The session concludes with the showcase on how to use AWS Lambda Powertools for Java to add logging, metrics, and traces to the application and run log insight queries for common use cases.

Speaker: Abhishek Gupta, Principal Developer Advocate, AWS India
Duration: 30mins

Move containerized applications to AWS (Level 200)
Containers have changed the way we develop, test, and deploy software as they make it faster to experiment and deliver value. Cloud provides flexibility, scalability, reliability, performance, and cost effectiveness. But how do you go about bringing these two worlds together? Is it possible to get all of the benefits of containers, and all of the benefits of the cloud? In this session, learn how to formulate a container migration strategy, containerize and migrate these workloads from your source to AWS. Uncover how to complete these migrations successfully, evaluate the methodology to choose specific migration method and lay the foundation for subsequent migration at scale.

Speaker: Joshua Samuel, Enterprise Solutions Architect, AWS
Duration: 30mins

Jumpstart your Amazon ECS solutions blueprint (Level 300)
As builders look to adopt containers and accelerate software delivery, they need to learn multiple aspects to build, deploy, run, monitor, and secure containerized applications. In this session, we provide the technical deep dive on Amazon ECS solution blueprints for AWS Fargate. With Amazon ECS solution blueprints, users can access Terraform code which provides a simpler starting point to learn by coding while making progress on their container adoption journey. Understand how Amazon ECS solution blueprints encode common architecture patterns and best practices, enabling you an easy yet proven pattern which is used by many builders.

Speaker: Glendon Thaiw, Solutions Architect, AWS
Duration: 30mins

Accelerate your deployments of web applications and API services on AWS App Runner (Level 300)
Web applications and APIs are vital for powering various aspects of customers' operations, ranging from user-friendly sites, mobile apps to complex backend services handling business logic. However, ensuring optimal deployment with scalability can be challenging due to the multitude of underlying resources and configurations involved. In this session, learn how to use AWS App Runner, for the full application life cycle from development to production. Understand how AWS App Runner enables you to simplify the entire process of running containerized web applications and APIs, so you can focus on building and refining applications, without worrying about handling complex infrastructure and deployment operations. We also demonstrate how to deploy APIs to power a web application.

Speaker: Farhan Angullia, Cloud Architect, Professional Services, AWS
Duration: 30mins

Build, run, and manage containerized application on AWS Fargate (Level 300)
Containers have emerged as a new standard for how we package and deploy our applications. In addition to managing our containerized applications, builders have to manage and maintain the servers on which these containerized applications run. In this session, learn how to build, run, and manage applications using AWS Fargate, a serverless compute engine to run containers in both Amazon Elastic Container Service (ECS) and Amazon Elastic Kubernetes Service (EKS) and eliminates the need to provision and manage servers or clusters of Amazon EC2 instances.

Speaker: Jayesh Kumar Tank, Senior Cloud Architect, AWS Professional Services, AWS India
Duration: 30mins

Accelerate Kubernetes adoption journey with Amazon EKS Blueprints (Level 300)
Containerization has transformed the way modern applications are developed. Join this session as we dive deep into Amazon EKS Blueprints, a collection of Infrastructure as Code (IaC) modules which helps you to configure complete EKS clusters that are fully bootstrapped with operational software needed to consistently deploy and operate workloads. Find out how to describe the configuration for the desired state of your EKS cluster, such as the control plane, worker nodes, and Kubernetes add-ons, as an IaC blueprint. Once a blueprint is configured, we share how to deploy consistent environments across multiple AWS accounts and regions using continuous deployment automation.

Speaker: Bin Liu, Senior Cloud Architect, AWS Professional Services
Duration: 30mins

High availability and resiliency design for your Amazon EKS workloads (Level 300)
Organizations require resiliency, availability, and disaster recovery for critical business systems to ensure reliability and stability. In this session, we outline the key characteristics of resilient workloads and disaster recovery patterns. We then dive deep into the tools including AWS Fault Injection Simulator to simulate failures and disaster scenarios for Kubernetes clusters on AWS, multi-cluster design for high availability and resilience, and the multi-region design for Amazon EKS. We also discuss the multi region considerations for database and storage, and share the key AWS resources you need to build a strong foundation for resiliency and high availability for your workloads.

Speakers: 
Vivekanand Tiwari, Cloud Architect, AWS Professional Services
Haofei Feng, Senior Cloud Architect, AWS Professional Services

Duration: 30mins

Karpenter: Just-in-time nodes for your Amazon EKS Clusters (Level 300)
In this session, learn how Karpenter, an open-source high-performance Kubernetes Cluster Autoscaler simplifies Kubernetes infrastructure with the right nodes at the right time. We cover how to setup Karpenter on Amazon EKS and simplify autoscaling and improve application availability. Learn how Karpenter automatically launches just the right compute resources to handle your cluster's applications. Take full advantage of the cloud with fast and simple compute provisioning for Kubernetes clusters with Karpenter.

Speaker: Ben Friebe, Senior ISV Solutions Architect, AWS
Duration: 30mins

Break barriers to Kubernetes with Red Hat OpenShift Service on AWS (ROSA) (Level 200)
With an increasing need to solidify security foundations, simplify operations and maintain hybrid environments, many who adopt containerization are often looking for a comprehensive approach to achieve positive impact on the multiple facets throughout their technological journey. In this session, learn the ingredients to build a successful platform and application strategy. We outline the main elements of a complete container platform including how to maintain compliance, disaster recovery, cost efficiency through the lens of Red Hat OpenShift Service on AWS (ROSA). Find out how to leverage built-in capabilities of ROSA including key integrations to AWS services, related patterns and tools to support your container migration.

Speaker: Will Garcia, Senior Partner Solutions Architect, Red Hat, AWS APJ
Duration: 30mins

Decoding modern architectures: where serverless meets microservices and monoliths (Level 200)
Tech advancements have made writing code and deployments easier but some challenges remain. How do you select the right architectures and technologies for your project and your business goals? Join this session as we dive deep into the benefits, drawbacks of monoliths, microservices, and how they intersect with serverless architectures. We dive deep into when each approach makes sense based on your requirements to achieve faster and more efficient delivery of solutions. We also cover practical tips on how to select the right technologies and AWS solutions to support your chosen architecture.

Speaker: Albert Blaya Perez, Solutions Architect, AWS
Duration: 30mins

Composing integration patterns in serverless microservices (Level 300)
Teams building microservices architecture often find that integration with other applications and external services can make workloads more monolithic and tightly coupled. Loosely coupled integration enables builders to easily design independent systems that can be developed and operated individually, and increase the availability and reliability of the overall system. Join this session to learn the key patterns for integration and how to use event-based architecture to decouple and decentralize application components using AWS Cloud Development Kit (AWS CDK). We then explore real-world use cases architected with cloud-native and serverless services. The session also features step by step guidance on how to choose the right integration technologies to suit your requirements.

Speaker: Donnie Prakoso, Principal Developer Advocate, AWS
Duration: 30mins

Building event-driven architectures on AWS (Level 200)
More organizations are looking at event-driven architectures to help with application modernization and building next-gen applications. But where do they start? In this session, we outline the key event-driven design concepts and how to leverage solutions such as Amazon EventBridge, Amazon Simple Notification Service, and Amazon Simple Queue Service. We dive deep into Amazon EventBridge event bus topologies, multi-account patterns, and best practices. At the end of the session, learn how to build loosely coupled applications, to scale independently, and making it easier to integrate cloud-based applications and services.

Speaker: Jan Tan, Principal Solutions Architect, AWS
Duration: 30mins

Unlocking lightning fast Lambda functions: Strategies for speed and efficiency (Level 300)
Are you looking for serverless compute that automatically manages underlying compute resources, scale seamlessly, and gracefully handling unexpected spikes in traffic? Do you wish to only pay for the actual compute time your code consumes? Join this session as we share how to build and optimize fast and efficient AWS Lambda functions. We walk through practical tips and best practices for monitoring, testing, and improving performance. We also explore the trade-offs between speed, cost and complexity, and how to find the right balance for your needs. Whether you are just starting out with AWS Lambda or are looking to hyper-optimize your functions, this session provides you the guide to creating cost-effective and high-performing serverless solutions.

Speaker: Chris Coombs, Solutions Architect, AWS
Duration: 30mins

AWS Step Functions: When to use and how to get the most out of it (Level 200)
AWS Step Functions is a service that enables you to coordinate your workflows so that your application development is faster and more intuitive. We share how AWS Step Functions, allows you to centrally manage a workflow by breaking it into multiple steps, adding flow logic, tracking the inputs and outputs between the steps. Learn how this low-code, visual workflow service, makes it fun for you to work with and easy to adopt. We also walk through the key features of AWS Step Functions which enable you to build distributed applications, automate processes, orchestrate microservices, as well as create data and machine learning (ML) pipelines. Understand how AWS Step Functions integrates with other AWS services, letting you call each service's API actions from your workflow. The session also covers the different pathways you can use to minimize your code and cost.

Speaker: Katherine Vishnevskaya, Solutions Architect, AWS
Duration: 30mins

Using serverless containers to rapidly deliver a generative AI chatbot application (Level 300)
Are you wondering how you can interface to and implement generative AI workloads for your organization and users? Join this session as we walk through a real-life use case of building a public user facing chatbot with generative AI. Find out how you can build this chatbot with AWS serverless and containers including AWS Lambda based containers, Amazon API Gateway, Amazon DynamoDB, with a Large Language Model (LLM) endpoint. We then demonstrate how to leverage these solutions to quickly build and deploy a resilient, secure generative AI powered chatbot application with minimal effort and cost. We also discuss how add context to generative AI workloads with Retrieval Augmented Generation (RAG) and automate deployments via CI/CD tools and AWS Lambda containers.

Speakers: 
Mai Nishitani, Solutions Architect, AWS
Steven Cook, Senior Solutions Architect, AWS

Duration: 30mins

Accelerate transformation on.NET monolith applications to microservices with AI and machine learning (Level 300)
Moving from monolithic to microservices involves multiple manual steps, which requires domain level knowledge and significant effort to manage this transition. In this session, we outline the challenges of transitioning from monoliths to microservices and benefits of microservices. Learn about the modernization solutions for applications built on Microsoft technologies and AWS tools that support Microsoft workload migration to the cloud. We share how to utilize AWS Microservice Extractor for .NET. to facilitate extraction of microservices from monoliths. We also review how to incorporate AI and machine learning in the modernization process, by showcasing how Microservice Extractor leverages AI-powered recommendations for valuable insights to optimize the microservices architecture.

Speakers: 
Kush Tiwari, Senior Applications Architect, AWS Professional Services
Tuan Huynh, Cloud Architect, AWS Professional Services

Duration: 30mins

Effectively using Java on serverless and containers (Level 300)
Java is one of the most widely used programming languages, for server-side language supporting many back-end development projects. In this session, learn how to optimize applications for serverless and containers. We share best practices, performance trade-offs, and design considerations so you can make well-informed decisions when bringing Java applications to serverless and containers.

Speaker: Abhishek Jawali, Senior Solutions Architect, AWS India
Duration: 30mins

Securing serverless applications on AWS (Level 200)
While serverless model takes away lot of responsibilities from you and allows you focus on creating business value, security is a constantly changing landscape that that should not be neglected. It is important to understand and manage security risks, such as XSS, XML, SQLI, and more. This session outlines the variations in attack vectors, prevention methods, and key considerations for securing your applications. We dive deep into best practices to ensure a proper security posture for your serverless applications including the right guardrails for avoiding potential pitfalls and security breaches.

Speaker: Utkarsh Pandey, Senior Startup Solutions Architect, AWS India
Duration: 30mins

Enhancing serverless resilience through observability (Level 200)
Many organizations are adopting serverless-first architectures to achieve high availability, reduce operating costs, and speed up time to market. However, the engineering and operations teams find it challenging to build resiliency into these microservice-based workloads. In this session, we explore best practices for serverless observability. We then demonstrate how to instrument resilience in your environment using logging, tracing, and monitoring in your serverless applications.

Speakers: 
Ankush Agarwal, Associate Solutions Architect, AWS India
Nishant Dhiman, Solutions Architect, AWS India

Duration: 30mins

Power your applications with generative AI on AWS (Level 200)
We are starting to see the widespread adoption of generative AI as many realize it opens unimagined possibilities in every customer experience and application. In this session, we review how to integrate your applications with generative AI on AWS in the key use cases such as content generation, summarization, enterprise search, and software development. Discover how to apply generative AI to address your needs and deliver value.
 
Speakers: 
Melwin Pais, Senior Solutions Architect, AWS
Naomi Teng, AI/ML Specialist, APJ, AWS

Duration: 30mins

Transform your contact center with generative AI call analytics (Level 200)
Generative AI is changing the way organizations deliver impactful customer experiences especially in the context of contact centers to uncover real-time and live call insights into customer conversations. With Large Language Models (LLMs), you can generate highly accurate call summaries, identify intent, problem signatures, agent actions, and sentiment analysis from call transcripts. However, performance, latency, token limits, and cost remain a barrier when using LLMs especially at scale. In this session, uncover a novel architecture as we walk through a teacher/student architecture by utilizing LLM to fine-tune a smaller LLM. Learn how you can get started easily to implement a low latency, high-quality call analytics and cost-effective generative AI powered call analytics solution on AWS.
 
Speaker: Nagib Shah, Solutions Architect, AWS India
Duration: 30mins

Personalizing your customer experiences with generative AI on AWS (Level 200)
Organizations are looking at leveraging AI and machine learning to deliver personalized customer experiences, in order to increase customer engagement, loyalty and sales. Join this session as we explore the various traditional AI and generative AI solutions to provide personalized customer experience and scale personalization in a cost-effective manner. The session includes a demo on how to use machine learning algorithms and analyze consumer data, to deliver highly relevant and personalized recommendations based on individual preferences, previous purchases, and browsing behavior.

Speaker: Tim Wu, Senior AI Specialist Solutions Architect, AWS
Duration: 30mins

Building generative AI use cases with privacy and security (Level 200)
The number of organizations using generative AI has been growing significantly as they expect significant effects on their industries and workforces. These organizations want to use generative AI tools for various benefits including increasing productivity, but are concerned about losing visibility on who are using the tools. Other concerns include sensitive or confidential data being leaked when they allow employees with unrestricted access to the tools and data. In this session, we review mechanisms on how to ensure the careful implementation of generative AI in a secure and private manner, ensuring organizational and customers’ data are secure and well-protected.

Speaker: Melwin Pais, Senior Solutions Architect, AWS
Duration: 30mins

Generative AI-driven emerging applications using Amazon SageMaker JumpStart, AWS AI services, and Large Language Models (LLMs) (Level 300)
There is an explosive level of interest on the use generative AI and the underlying technologies, but many are trying to figure out how to harness its potential to deliver value. Join this session as we share how to use generative AI for key use cases, build conversation-style applications for generating and analyzing content with focus on image generator, content generator, and image analyzer while keeping your responses within your organization. We then dive deep into popular use cases and architecture patterns you can apply in your projects. This session also includes a demo on how to use Amazon SageMaker JumpStart, AWS AI services, LLMs, LangChain and Streamlit framework on key use cases.

Speaker: Arman Sharma, Senior Solutions Architect, AWS
Duration: 30mins

Generative AI patterns on AWS: Exploring modern applications with generative AI (Level 200)
Generative AI offers the potential to transform the way we interact, as you can create new content that are both realistic and creative by learning from large datasets of text, images, and code. It opens up the possibility of developing a wide range of applications for a variety of use cases. This session covers the guidelines on when to apply RAG, vs. fine-tuning vs. prompt engineering, to improve generative AI performance. We explore some of the solutions that use generative AI models in conjunction with AWS building blocks such as Amazon SageMaker and Amazon SageMaker JumpStart to solve common use cases including question and answer, summarization, simplification, and tone augmentation. We explain when and how to use advanced prompt engineering, fine-tuning, and RLHF options to improve the results and demonstrate one of the patterns.

Speaker: Arun Balaji, Principal Prototyping Engineer, AWS India
Duration: 30mins

Addressing Responsible AI and AWS generative AI offerings (Level 200)
Generative AI models that produce open-ended and unconstrained content pose additional challenges for responsible AI. They raise new issues around fairness, toxicity, intellectual property, hallucinations, and privacy. Organizations attempt to address these challenges through complex governance and oversight processes, rigorous audits, and filters on the generated content and constantly solicit user feedback but this requires a lot of effort, time, and resources. With the proliferation of unstructured data that is incorporated into new algorithms and applications using generative AI, it is imperative to establish a strategy for responsible AI that can withstand this new age. In this session, we explain how to generate innovative and useful content on a large scale and maximize the potential of generative AI while addressing the concerns around responsible AI.

Speakers: 
Gaurav Singh, Solutions Architect, AWS India
Smiti Guru, Senior Solutions Architect, AWS India

Duration: 30mins

Content moderation with low to no code orchestration powered by traditional AI solutions and generative AI (Level 200)
Volume of user-generated content or UGC is increasing exponentially across every platform, providing organizations with the opportunities to connect with their customers. But there are challenges in ensuring the content remains safe and compliant, and how to limit customer exposure to inappropriate UGC. In this session, we share how to create a scalable content moderation solution with AWS AI/ML services and generative AI on AWS tools. We walk through the steps to shift moderation process left and ways to mitigate issues early. Learn how you can reduce reliance on manual processes to speed up the review process, and improve the accuracy and analysis. We then explore generative AI on AWS tools to enhance content moderation by generating realistic examples of harmful content, allowing models to be trained to recognize previously unseen variations. At the end of the session, walk away with the knowledge on tools, steps and guidance to ensure your content moderation becomes more efficient, effective and provide a safer and more inclusive online environment for your users.

Speakers: 
Sam Gordon, Senior Cloud Architect, AWS Professional Services
Ed Fraga, Cloud Architect, AWS Professional Services

Duration: 30mins

Builders’ guide to modern application development (Level 200)
Join this session as we explore the tools which enable you to host code, build, test, and deploy your applications quickly and effectively. We walk through some of the core tools including the AWS Toolkit within your IDE of choice to access your AWS environment, Amazon CodeCatalyst, an integrated service for software development teams looking to adopt continuous integration and deployment practices into the software development process. Depending on what you are building, the session offers guided best practices and abstractions on how you can improve agility, security, velocity, and code quality.

Speaker: Donnie Prakoso, Principal Developer Advocate, AWS
Duration: 30mins

Tools for modern apps with serverless and containers (Level 300)
AWS offers tools for builders to run your modern applications, including those looking at containers and serverless architectures. In this session, learn where to start, tools available and how you can accelerate your development process without compromising on quality. We demonstrate the use of key builder tools through a real use case demo, and walk through with step by step guide on building production-ready applications in no time. This session also showcases how to leverage AWS Copilot CLI to build, release, and operate containerized applications, and AWS SAM CLI to take your serverless applications from local code, execution and testing to pipeline-driven deployments.

Speakers: 
Chen Xin, Senior Cloud Architect, AWS Professional Services
Niko Eckerskorn, Principal Cloud Architect, AWS Professional Services

Duration: 30mins

Improve your approach to building Infrastructure as a Code with AWS Cloud Development Kit (AWS CDK) (Level 200)
Composing infrastructure using a programming language and AWS Cloud Development Kit (AWS CDK) creates many new possibilities looking to accelerate cloud development. In this session, understand how you can build infrastructure differently with AWS CDK. We focus on practical advice that can help you improve your Infrastructure as code with new ways to develop and deploy your infrastructure and applications while achieving higher levels of reusability.

Speaker: Guy Morton, Senior Solutions Architect, AWS
Duration: 30mins

From code to production – Building .NET natively on AWS (Level 300)
Join this session as we walk through how .NET is used to build a cross platform application and delivering messages to an AWS IoT backend. We then showcase how the backend is aggregating and storing these messages before sending to a real-time dashboard to show the results. Learn the best practices you can use when approaching your next .NET application to run on native AWS services. We also explore the IAC and automation tools you can utilize to ensure your updates and new features are seamless.

Speaker: Derek Bingham, Senior Developer Advocate, AWS
Duration: 30mins

Building always available applications with AWS Amplify and Flutter (Level 200)
Many applications can benefit from continuous operations even when they are not online. This is especially important for mobile applications, which must continue to provide an optimal user experience even when there is intermittent connectivity. In this session, discover how AWS Amplify and AWS AppSync enable you to build complex backends and connect your application to multiple data sources. Learn how AWS Amplify DataStore easily creates an online-offline mobile application with Flutter. We show a working demo of a Flutter application and explain how to implement these capabilities in a mobile application.

Speakers: 
Sakthi Srinivasan, Engagement Manager, AWS India
Sureshkumar K V, Prototyping Architect, AWS India

Duration: 30mins

Build an app in minutes with AWS Amplify Studio and AWS App Composer (Level 300)
Have you been thinking of a great idea you wished you could build an application for your use case? Don’t miss this session where we share how to visually design and build powerful applications in the cloud in the matter of minutes with AWS Application Composer and Amplify Studio UI Library. We explain through a demo on how to design UI components and convert them to code with AWS Amplify Studio UI Library. This session also features how to integrate the AWS Serverless services and build fully functional application backends with AWS Application Composer.

Speakers: 
Thong Seng Foo, Senior Solutions Architect, AWS
Windrich, Associate Solutions Architect, AWS

Duration: 30mins

Maximizing serverless application potential with storage (Level 200)
Modern applications have revolutionized application architecture. With serverless, builders can focus on product innovation and speed up time to market without worrying about provisioning, maintaining, and scaling servers for backend components. In this session, learn about the AWS storage options for the serverless use cases such as Amazon S3 and Amazon Elastic File System (Amazon EFS). Understand how to determine which storage is the best fit for your modern application use cases.

Speaker: Lily Jang, Storage Business Development Manager, AWS
Duration: 30mins

Speed up application development with managed serverless databases (Level 200)
Many organizations are looking at highly distributed applications leveraging purpose-built databases and how to build internet-scale applications which require diverse data models. In this session, we cover the requirements for those looking to build modern applications. Find out how AWS purpose-built databases meet the scale, performance, and manageability requirements of modern applications. We then dive deep into how these managed and serverless databases can assist your application development and remove the heavy lifting. The session concludes with a discussion on the different data models, where, and how each of the AWS serverless offerings can help.

Speakers: 
William Wong, Principal Database Solutions Architect, AWS
Surendar Munimohan, Senior Database Solutions Architect, AWS

Duration: 30mins

Transitioning your application workloads to AWS Graviton (Level 200)
AWS Graviton provides a wide selection of instance types optimized to fit different use cases. The instance types comprise of varying combinations of CPU, memory, storage, and networking capacity. The transition to arm with AWS Graviton can be as simple as updating your infrastructure as code. Join the session as we provide step-by-step approach on how to assess your workloads, identify, and address potential software changes that are required so you can enjoy the performance and cost benefits of AWS Graviton. Learn how to choose the appropriate mix of resources for your applications and scale your resources based on your workload requirements.

Speakers: 
Joao Palma, Senior Cloud Architect, AWS Professional Services
Igor Londero Gentil, Senior Cloud Architect, AWS

Duration: 30mins

Generative AI for builders: How to build innovative solutions with AWS (Level 300)
In this session, learn what is generative AI on AWS and the benefits of leveraging the technologies to deliver outcomes including how to reinvent your applications, create innovative customer experiences, and drive unprecedented levels of productivity. We explain the AWS services and tools to build and deploy generative AI models. Understand the examples on generative AI applications in various domains and industries. We also share the tips for designing and testing generative AI solutions.

Speaker: Vatsal Shah, Senior Solutions Architect, AWS India

Build a generative AI call analyzer front end application (Level 300)
Generative AI and Large Language Models (LLMs) can add conversational style features to your contact center application. This session showcases the step by step guide through a demo on how to build a generative AI call analyzer, a front-end application based on Python Streamlit framework. We walk through how to upload an audio conversation which consist of a contact center recording and then covert audio into transcripts with Amazon Transcribe. We show how to convert text to vector embeddings and use LLMs for creating summarization, sentiment analysis, call analytics, language translation, and Q&A. Walk away with the knowledge you can use to try on a call transcription and analytics use case using LLMs available on Amazon SageMaker JumpStart.

Speaker: Arman Sharma, Senior Solutions Architect, AWS

Creating superhero avatars with generative AI on AWS and Stable Diffusion (Level 200)
Stable Diffusion is a deep learning model that allows you to generate realistic, high-quality images and stunning art in just a few seconds. Join this session as we demonstrate how to create your own superhero avatar with Stable Diffusion and Amazon SageMaker JumpStart, With Amazon SageMaker JumpStart, you can access a pre-trained Stable Diffusion model that can generate superhero avatars based on your preferences. We conclude with providing you with the step by step guide on how to apply these technologies into your own projects.

Speaker: Vatsal Shah, Senior Solutions Architect, AWS India

Build a multi-functional chatbot with Amazon SageMaker JumpStart (Level 200)
Join this session as we show how to leverage the foundation models provided by Amazon SageMaker JumpStart to build a multi-functional chatbot. We walk through how to build chatbot which can generate both images and texts, by deploying two types of FMs; text-to-image model and text-to-text generation models, which are provided by Amazon SageMaker JumpStart. Learn how to use these similar steps to build your own applications powered by generative AI with AWS to transform your customer experience.

Speaker: Melanie Li, PhD, Senior AIML Specialist Technical Account Manager, AWS

Generative AI and natural language query for BI (Level 200)
Dashboards are meant to answer questions. While some questions are easy to anticipate for dashboard authors, but what happens when ML-generated insights, such as anomaly in the data surface questions that dashboard authors did not anticipate. Join this session as we show how to leverage generative AI and natural language query capabilities to enable your users to answer ad-hoc questions on-the-fly, with no technical skills needed.

Speaker: Michael Armenanto, Senior GTM Specialist, AWS

Enhancing chatbot performance with generative AI using Amazon Kendra and Amazon SageMaker hosted LLMs (Level 300)
In this session, learn how to implement Retrieval Augmented Generation (RAG) using Amazon Kendra and SageMaker hosted LLM (Large Language Models) to address data privacy and data residency concerns. We showcase how you can combine RAG with Amazon Kendra, a semantic search service, can significantly improve the response quality of chatbots and eliminate hallucination, while ensuring data privacy. Find out how to deploy LLM in Amazon SageMaker in a cost effective and optimized way, as well as integrate RAG and LLM with existing chatbot infrastructure to provide a seamless user experience. The session also outlines the benefits and practical applications of RAG enabled by Amazon Kendra and SageMaker hosted LLM, empowering you to create secure, responsive, and intelligent chatbots.

Speaker: Ben Friebe, Senior ISV Solutions Architect, AWS