15:30 - 16:00 Session Block 7

Using SageMaker AI to host and serve in-house built machine learning models and lessons learned when using SageMaker in production environment.

As AI adoption accelerates, the focus is shifting from single-shot prompts and chat interfaces to persistent, intelligent agents that can plan, act, and collaborate with both humans and tools. But deploying such agents in production—especially in infrastructure or DevOps-heavy contexts—requires more than LLM magic. It requires architecture.

This talk walks you through how to build interruptible, tool-calling AI agents that can reason over tasks, handle human input in the loop, cooperate with other agents, and call external tools or APIs dynamically—using modern techniques like Model Context Protocol (MCP), loop debugging, and event-based interruptions.

Launching generative AI applications requires careful considerations around model selection and evaluations, fine-tuning versus RAG, security, privacy, hallucination control, and cost management. In this session, dive into some common architecture patterns, security guardrails, governance approaches, and optimization tricks that have been developed to support hundreds of AWS customers

This panel brings together industry leaders, policymakers, and technology experts to explore the current state and future potential of digital transformation across Bosnia and Herzegovina. The discussion will focus on public and private sector initiatives, cloud adoption, digital infrastructure, regulatory challenges, and the role of innovation and talent in accelerating the country’s digital journey. Join us as we examine how technology can drive economic growth, improve services, and position BiH on the regional digital map.

In event-driven systems, understanding how data flows through decoupled services is essential—but not always straightforward. Distributed tracing provides the visibility needed to debug issues, monitor performance, and maintain operational resilience at scale.

In this session, we’ll explore how to implement distributed tracing across event-driven architectures on AWS, including scenarios where events originate from external sources like Apache Kafka. You’ll see how AWS CloudWatch and AWS X-Ray can be used together to trace asynchronous workflows involving Lambda, SNS, SQS, and EventBridge—even when they interact with off-AWS systems.

Step into a session where inspiration meets action — designed to uplift and empower women in the cloud and tech industry. This isn’t just a talk; it’s your opportunity to grow, connect, and take real steps forward in your journey. We’ll dive into how to amplify your voice, navigate public speaking, start contributing to community events, and build lasting professional networks. Whether you’re exploring the first steps or ready to lead, you’ll find practical advice, fresh perspectives, and plenty of encouragement.