Dhiraj Mahapatro

Production AI agents need orchestration that handles non-deterministic behavior, multi-hour workflows, human approvals, and multi-agent coordination. Learn how AWS Step Functions and AWS Lambda durable functions provide the reliability layer that agents demand.

Discover how to architect scalable, production-ready agentic AI applications on AWS that deliver autonomous, multi-agent solutions for complex business challenges. Many organizations struggle with designing AI agents for real-world complexity, from managing context effectively to ensuring secure, scalable deployments.

Agentic AI is transforming enterprise applications, but taking it from prototype to production requires more than just prompting. Join this chalk talk to discuss pragmatic, scalable patterns for building agentic AI systems using AWS Serverless services like Lambda, ECS Fargate, and API Gateway.

While AI agents offer powerful automation capabilities, many critical business workflows require human oversight and approval. This 20-minute lightning talk demonstrates practical patterns for integrating human-in-the-loop (HITL) controls within multi-agent AI systems.

In this chalk talk, explore how to architect a serverless AI gateway on AWS to securely integrate and consume large language models from multiple providers. Explore model abstraction, monitoring, observability, governance, security, compliance, and auditing.

Learn to harness the power of AWS Serverless to build robust, cost-effective generative AI applications in this breakout session. Explore using AWS Step Functions to orchestrate complex AI workflows seamlessly.

Event-driven architectures help you build production-grade applications quickly from the ground up. However, not every workload is a greenfield application, and many customers prefer to manage their business logic on containers using either Amazon ECS or Amazon EKS.

Building distributed solutions with functions and microservices often requires coordinating workflows. You may need a data processing workflow that coordinates multiple services like AWS Lambda, Amazon S3, and Amazon Athena.

With the advancement of serverless, using Java as a runtime for AWS Lambda functions became an immediate approach for enterprises that wanted to use Java and accelerate on the AWS Cloud. These enterprises also experienced Java cold starts in Lambda functions firsthand.

Building distributed solutions with functions and microservices requires orchestrating workflows. You might need a workflow for engineers to request cloud resources and managers to approve requests.