Agenda

AWS Summit India Keynote

• 10:00 AM - 12:30 PM

  AWS Summit Bengaluru Keynote - Recap
  

• 12:30 PM - 1:30 PM IST

  Break

• Breakout tracks

  • Track 1 - Generative AI for builders

     

    Amazon Bedrock - Simplifying generative AI app development
    

    Time: 1:30 - 2:00 PM IST
    Level: 100 - Introductory
    

    What to learn how to quickly and easily develop generative AI applications with Amazon Bedrock?
    Amazon Bedrock is the easiest way to build and scale generative AI applications with LLMs and other FMs. You enjoy the broadest choice of models - many of which are available first, or only, on Bedrock. You can add your own business context quickly, easily, privately – with the broadest selection of customization options. With Amazon Bedrock, developers can access a wide range of pre-trained AI models from leading AI startups and Amazon's own Titan models, as well as the ability to train their own custom models on large datasets. It provides agents, RAG, model evaluation and is encapsulated with responsible AI (guardrails) and much more.

    Speaker:
    Sahil Verma, Senior Solutions Architect, AWS India
    

    ---

    MongoDB
    

    Time: 2:00 - 2:30 PM IST

    TBD

    Powering generative AI applications with AWS purpose-built infrastructure

    Time: 2:30 - 3:00 PM IST
    Level: 300 - Advanced
    

    What is the purpose-built infrastructure that powers innovative generative AI applications on AWS? This session provides a behind-the-scenes look at how AWS Trainium and AWS Inferentia2 accelerators enable Amazon teams and AWS customers to build, deploy, and scale high-performance generative AI models at optimized costs. Learn how organizations across industries are leveraging the secure, innovative, and performant AWS Cloud to solve complex challenges, turn groundbreaking ideas into reality, and deliver innovative solutions at scale.

    Speaker:
    Ashwini Kumar, Senior Specialist Solutions Architect, AWS India
    

    ---

    Unlock the power of no-code AI: Explore Amazon SageMaker's LLM driven capabilities
    
    Time: 3:00 - 3:30 PM IST
    Level: 200 - Intermediate

    Learn to use the no-code Amazon SageMaker experience to build and use large language models (LLMs). See how to complete the entire ML lifecycle, including data exploration and preparation, using a new LLM-powered natural language interface, model building, and deployment without any code. Dive deep into new LLM capabilities, including how to compare outputs from multiple FMs and select the best FM to perform business analysis.

    Speakers:
    Gaurav Singh, Senior Solutions Architect, AWS India
    Aparajithan Vaidyanathan, Principal Enterprise Solutions Architect, AWS India
    

    ---

    Unleash the potential of prompt engineering: Optimize your LLMs on Amazon Bedrock
    

    Time: 4:00 - 4:30 PM IST
    Level: 200 - Intermediate

    Prompt engineering is the process of guiding large language models (LLMs) to produce desired outputs. In this session, get an overview of prompt engineering best practices and learn how to choose the most appropriate formats, phrases, words, and symbols to get the most out of generative AI solutions while improving accuracy and performance. This session uses the Claude 2 LLM as an example of how prompt engineering helps to solve complex customer use cases. Also learn how prompts can be integrated with your architecture and how to use API parameters for tuning the model parameters using Amazon Bedrock.

    Speaker:
    Senthil Jeyachandran, AI & ML Specialist Solutions Architect, AWS India
    

    ---

    Supercharge your development with AWS generative AI developer tools
    

    Time: 4:30 - 5:00 PM IST
    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.
    

    Speaker:
    Ramesh Ranganathan, Senior Partner Solutions Architect, AWS India
    

  • Track 2 - AWS for data

     

    Build a data foundation to fuel generative AI
    

    Time: 1:30 - 2:00 PM IST
    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.
    

    Speaker:
    Niyati Upadhyay, Solutions Architect, AWS India
    

    ---

    Unlock insights from data on Amazon RDS by leveraging zero- ETL to Amazon Redshift
    

    Time: 2:30 - 3:00 PM IST
    Level: 300 - Advanced
    

    Discover how to unlock your data in Amazon RDS for MySQL and make it available in Amazon Redshift with the new zero-ETL integration. Once the data is in Amazon Redshift, you can power analytics and AI/ML workloads with materialized views, federated access to multiple data stores, and seamless integrations with Amazon SageMaker, Amazon QuickSight, and more. In this session, learnhow the Amazon RDS for MySQL zero-ETL integration with Amazon Redshift can help you solve typical challenges with building and operating data pipelines. See demos of a zero-ETL setup, ongoing data and schema replication, and monitoring. Learn why and when you should use this powerful capability to accelerate your data strategy.

    Speakers:
    Deep Dey, Database Solutions Architect, AWS India
    Dipayan Sarkar, Senior Analytics Specialist Solutions Architect, AWS India
    

    ---

    Deep dive on Amazon S3 Express One Zone storage class
    

    Time: 3:00 - 3:30 PM IST
    Level: 300 - Advanced
    
    The Amazon S3 Express One Zone storage class delivers one of the fastest and lowest-latency cloud object storage for performance-critical applications that demand consistent single-digit millisecond latency and the ability to scale to millions of requests per minute for frequently accessed datasets. In this session, learn about this new single Availability Zone storage class, its new S3 directory buckets, and how you can now collocate storage and compute in the same AWS Availability Zone for more efficient use of compute resources and lower TCO. In addition, hear from Pinterest on how they improved the latency of one of their most critical applications.
    

    Spraker:
    Sandeep Aggarwal, Solutions Architect , Storage, AWS India
    

    ---

    Generative BI in Amazon QuickSight
    
    Time: 4:00 - 4:30 PM IST
    Level: 300 - Advanced

    You can infuse generative AI into how your business users interact with data. In this session, learn how Generative BI capabilities in Amazon QuickSight allow business analysts to author dashboards using natural language and how business users can easily dive deep into data by simply asking questions. Discover how business users can also use Generative BI capabilities to quickly create compelling stories to drive decision-making, while developers can integrate these capabilities into applications to differentiate and monetize data like never before.
    
    Speaker:
    Aneek Arora, Quick Sight Solutions Architect, AWS India
    

    ---

    Running Amazon ElastiCache as Machine Learning(ML) feature store to serve million queries per second with ultra low latency. Learn how Swiggy uses Amazon ElastiCache to deploy its Machine Learning feature.

    Time: 4:30 - 5:00 PM IST
    Level: 300 - Advanced

    Amazon ElastiCache is a fully managed, Redis- and Memcached-compatible service delivering real-time, cost-optimized performance for modern applications. In this sessions we also also see how a Decacorn uses Amazon Elasticache innovatively as ML Feature store with data size in access to billion records with millions being actively retrieved during model inference, all while operating with Ultra low latency constraints.
    

    Speakers:
    Smita Srivastava, Solutions Architect, AWS India
    Shri Nath Agarwal, Software Developer IV, Swiggy
    

  • Track 3: Build on AWS

     

    Migrating to Amazon EKS delivers cost savings, reliability gains and accelerates development for BigBasket
    

    Time: 1:30 - 2:00 PM IST
    Level: 200 - Intermediate

    BigBasket is India's largest online food and grocery store. They operate in multiple eCommerce channels such as Quick Commerce, Slotted delivery, and Daily Subscriptions. Customers can also buy products from their physical stores and Vending machines. They offer a large assortment of over 50 thousand products and are operating in over 500 cities & towns. BigBasket service to over 10 million customers.
    By migrating from self-managed Kubernetes clusters to Amazon EKS, BigBasket has achieved significant cost savings, improved reliability, and faster development cycles. With Amazon EKS, BigBasket has reduced their operations overhead by 60% as fewer engineers are required to manage Kubernetes infrastructure. Deployment failures due to API throttling have been eliminated completely. Across 6 environments, over 100 microservices have been migrated to Amazon EKS, enabling faster feature development. Overall release velocity has improved by 35%. Just as importantly, BigBasket has seen a drastic reduction in production downtime events since moving to Amazon EKS. The combination of increased agility and higher reliability has been transformational for BigBasket.
    

    Speakers:
    Ayush Kumar, Solutions Architect, AWS India
    Sushant Gulati, Senior Engineering Manager, DevOps, Cloud & Platform, Big Basket

    ---

    Cast AI
    

    Time: 2:00 - 2:30 PM IST

    TBD

    Live streaming amplified with AWS purpose-built tools
    

    Time: 2:30 - 3:00 PM IST
    Level: 200 - Intermediate

    Delivering high-quality live and on-demand media globally is crucial in the digital age. AWS offers purpose-built services for organizations to reliably deliver, monetize, and support internet media, enabling unparalleled viewing experiences. This session showcases highly available architecture/s using AWS Solutions Library for reliable real-time viewing experiences. It covers live video streaming solutions for cost-effective global delivery and the AWS Countdown Service for optimizing critical event launches using proven AWS expert playbooks.

    Speakers:
    Mohammed Nawaz Shaikh, Technical Account Manager, AWS India
    Somnath Chatterjee, Senior Technical Account Manager, AWS India
    

    Redis
    

    Time: 3:00 - 3:30 PM IST

    TBD

    ---

    Using generative AI to add tailored product summaries to an app
    

    Time: 3:00 - 3:30 PM IST
    Level: 200 - Intermediate

    Building tailored product summaries helps to better target your audiences, but it is time-consuming. The more attributes you consider to describe your audience, the more attribute combinations you get and the more distinct product summaries you have to write. In this chalk talk, explore how to use foundational models through Amazon Bedrock to generate product summaries from a survey application. See tailored product summaries crafted about the 200+ AWS service offerings based on the role of survey respondents, their maturity with AWS, the services they already know, and the services they want to know more about.
    

    
    Speaker:
    Mayur Bhagia, Principal Solutions Architect, AWS India
     

    ---

    Harnessing generative AI to build data-driven brands
    

    Time: 4:00 - 4:30 PM
    Level: 200 - Intermediate
    

    In this chalk talk, learn about the evolving landscape of CPG companies as they transition into data-centric organizations, leveraging AWS Cloud infrastructure and generative AI using Amazon Bedrock. Learn about rapid development tools that empower CPGs to quickly deliver AI-driven use cases for R&D, advertising, revenue growth, and their product catalogs. Gain insights on how you can deploy intelligent virtual assistants that augment customer engagement and manufacturing using Amazon Bedrock and Anthropic’s Claude models. Walk away with a blueprint on how you can bring value to your organization with AWS infrastructure and generative AI.
    

    Speaker:
    Yogish Kutkunje Pai, Senior Solutions Architect, AWS India
                     

    ---

    Harness the power of AWS to build game-changing applications
    

    Time: 4:30 - 5:00 PM IST
    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.
    

    Speaker:
    Santosh Kumar, Senior Specialist Solutions Architect, AWS India
    

  • Track 4 - Security, compliance and resilience

     

    Take data protection from theory to practice on AWS
    

    Time: 1:30 - 2:00 PM IST
    Level: 200 - Intermediate

    As India enacts its Digital Personal Data Protection Act 2023 (DPDP), data protection becomes critical . In this session, you will understand how native AWS data protection services can provide you with granular controls over access , implement encryption , audit and policy enforcement - allowing you to build a highly secure foundation for your data. This session is suited for security leaders and builders , who need to understand data protection capabilities to meet compliance requirements and best practice implementations – basic understanding of AWS security services is recommended

    Speaker:
    Rajendra Shastrakar, Principal Security Architect, AWS India
    

    ---

    Best practices for creating multi-Region architectures on AWS
    

    Time: 2:30 - 3:00 PM IST
    Level: 300 - Advanced

    Architecting and building a multi-Region architectures can come with a new set of challenges. These challenges include how to manage dependencies, infrastructure deployments, data replication, consistency, observability, testing, and operations. Whether you’re needing to expand to multiple Regions to improve resilience, adhere to governmental data regulations, or improve end-user latency, this session highlights best practices, design principles, and sample architectures to help you meet your requirements.
    

    Speakers:
    Sornavel Perumal, Senior Technical Account Manager, AWS India
    Anshika Gupta, Technical Account Manager, AWS India
    

    ---

    Navigating digital sovereignty with more control and choice
    

    Time: 3:00 - 3:30 PM IST
    Level: 200 - Intermediate

    Organizations are facing increasing complexity in an evolving sovereignty landscape. AWS customers have shared concerns about choosing between the full power of AWS and feature-limited sovereign cloud solutions that could hamper their ability to innovate and grow. AWS believes that organizations shouldn’t have to compromise. In this session, discover how the AWS sovereign-by-design approach provides organizations with the most advanced set of sovereignty controls and security features, and learn how AWS offers infrastructure choice to support unique workload needs and local regulations. See real-word examples of how customers are using AWS’s range of sovereign offerings today.
    

    Speaker:
    Kush Vyas, Security Solutions Architect, AWS India
     

    ---

    Threat modelling to evaluate the security and resilience of your generative AI workloads
    

    Time: 4:00 - 4:30 PM
    Level: 200 - Intermediate
    

    This session guides you through a practical approach, empowering you to create a threat model for your own generative AI applications. See a demo of how to implement effective mitigations to secure your generative AI workloads with Amazon Bedrock. Additionally, learn about the AWS resilience lifecycle, a mental model for resilience on AWS. Come gain confidence to securely build your next generative AI workload on AWS, as well as meet your long-term resilience objectives.
    

    Speakers:
    Ankush Agarwal, Solutions Architect, AWS India
    Atul Dambalkar, Senior Solutions Architect, AWS India
                     

    ---

    Backup and disaster recovery strategies for increased resilience
    

    Time: 4:30 - 5:00 PM IST
    Level: 300 - Advanced
    

    Join this session to learn about different strategies for using AWS services to protect your on-premises and cloud-based applications against downtime and data loss. Discover how cloud technology can simplify your disaster recovery implementation while lowering total cost of ownership (TCO). In addition, take a deeper dive into AWS Elastic Disaster Recovery, and learn how this service can help organizations achieve recovery point objectives (RPOs) of seconds and recovery time objectives (RTOs) of minutes, as well as protect against, respond to, and recover from ransomware events.
    

    Speakers:
    Rajat Agarwal, Senior Technical Account Manager, AWS India
    Saikat Dey, Technical Account Manager, AWS India