AI Agents demystified

AWS re:Invent 2024 | AI Sessions and No-Code Tools

Written by Aimee Bottington | Nov 26, 2024 4:41:28 AM

AWS re:Invent 2024 is brimming with opportunities for tech enthusiasts, AI professionals, and enterprise leaders to explore the latest advancements in artificial intelligence and generative AI. This year’s sessions focus on groundbreaking techniques, scalable solutions, and real-world applications of AI that are revolutionizing industries.

At Integrail, we are thrilled to sponsor this event and share our expertise in Agentic AI. As a platform that enables businesses to create and deploy no-code AI applications, we have identified the top sessions that align with our mission to transform how AI is built, scaled, and integrated. Here’s our curated list of sessions to supercharge your re:Invent experience.

AIM306 | Tool Use & Agents at the Frontier: Advanced Techniques for LLM Actions

Unlock the true power of Large Language Models (LLMs) by transforming them from passive responders to active agents. This session delves into integrating LLMs with real-world systems via APIs, enabling automation and seamless interaction with other applications. Discover advanced prompt engineering techniques and frameworks like Amazon Bedrock Agents that extend AI capabilities.

Why Attend?

  • Learn to bridge the gap between LLM knowledge and actionable automation.
  • Explore cutting-edge use cases for Anthropic’s Claude models within Amazon Bedrock.
  • Boost your understanding of designing AI-driven tools for complex workflows.

AIM276-INT | Generative AI in Action: From Prototype to Production

Generative AI is no longer a futuristic concept—it’s a driving force behind scalable, production-ready solutions. This session covers best practices for developing GenAI applications, from robust data strategies to low-code/no-code development tools that democratize AI implementation.

Why Attend?

  • Master the transition from prototypes to enterprise-grade GenAI systems.
  • Gain actionable insights into data governance and cost-effective deployment strategies.
  • Understand how to integrate business users into the development cycle for maximum impact.

CMP331-R1 | Build and Accelerate LLMs on AWS Trainium and AWS Inferentia Using Ray

Efficiently scaling LLMs is a critical challenge for enterprises, and this session demonstrates how to leverage AWS Trainium and Inferentia for cost-effective, high-performance deployments. Practical techniques like tensor parallelism and Ray’s compute framework are highlighted.

Why Attend?

  • Explore state-of-the-art tools for scaling LLMs with performance optimization.
  • Understand how to reduce costs while maintaining model efficiency and accuracy.
  • Learn integration strategies for AWS’s advanced AI hardware.

AIM258-S | Building AI Agents in Slack Using AWS Services

Transform Slack into a powerful AI-driven workspace. This session teaches you how to build AI agents that integrate seamlessly into Slack workflows, automate complex processes, and connect with enterprise data using AWS Bedrock.

Why Attend?

  • Learn to create AI-powered agents tailored to organizational needs.
  • See how to securely integrate enterprise data into agent workflows.
  • Understand the synergy between Agentforce and Slack for enhanced productivity.

INO201 | Learning from Amazon: AI/ML + Generative AI

Amazon’s innovative use of AI across retail and consumer operations is a masterclass in scaling AI for real-world applications. This session provides invaluable lessons on how cultural, technological, and procedural strategies contribute to their success.

Why Attend?

  • Gain behind-the-scenes insights into Amazon’s AI strategies.
  • Learn how generative AI enhances efficiency and customer experiences.
  • Discover the interplay of AI/ML in launching new business initiatives.

GAM310 | Scaling Generative AI Models for Millions of Users in Roblox

Dive into the architecture and tools Roblox uses to support millions of users with generative AI. This session explores distributed workloads, compute orchestration, and ML application development.

Why Attend?

  • Learn best practices for scaling generative AI for mass adoption.
  • Understand how to design robust AI infrastructure for high-demand use cases.
  • Gain insights into developing SDKs for efficient ML deployment.

STP002 | AWS Generative AI Accelerator Spotlight: Base39

Get inspired by cutting-edge applications from the AWS Generative AI Accelerator. Base39’s innovative use of LLMs for credit and loan management highlights how AI can reshape industries.

Why Attend?

  • Explore impactful use cases of GenAI in finance and beyond.
  • Understand how LLMs and graph analysis power decision-making applications.
  • Network with trailblazers in AI innovation.

AES307 | Getting Better Image Analysis with Generative AI

This session addresses the nuances of leveraging generative AI for image analysis, from crafting effective prompts to ensuring data relevance. It’s perfect for industries like media, healthcare, and aerospace.

Why Attend?

  • Gain practical tips for improving image analysis workflows.
  • Learn how to use generative AI to deliver faster, higher-quality results.
  • Address challenges like flexibility and data timeliness.

Why These Sessions Matter

These sessions embody the future of AI—scalable, actionable, and deeply integrated into real-world applications. At Integrail, we are excited to see how these advancements align with our mission of simplifying AI workflows, enabling businesses to design and deploy Agentic AI effortlessly.

Join Us at AWS re:Invent 2024

Whether you’re an AI builder, enterprise leader, or tech enthusiast, these sessions will provide you with the insights and tools to thrive in an AI-driven world.

Be sure to visit Integrail at the event (Booth #977) to learn how our AI Studio can help turn these learnings into actionable solutions.

If you’re attending, book an onsite meeting with our experts to discuss tailored solutions for your business.

Follow our updates on LinkedIn and Twitter for more coverage from AWS re:Invent 2024!