Kamen Sharlandjiev

Data engineers spend weeks building pipelines describable in a single sentence. AI agents change this by autonomously discovering data, building transformations, and orchestrating workflows via natural language.

AI agents have moved beyond chat and have become autonomous operators of complex data workflows. But an agent is only as capable as the services it can reach. In this session, discover how AWS Analytics MCP Servers give AI agents native access to analytics services — and see through live demonstration, how to turn natural language into real data operations across query engines, transformation pipelines, and orchestration layers.

Organizations looking to orchestrate ETL data pipelines on AWS need tools that meet their requirements. In this chalk talk, learn about the pros and cons of orchestrating ETL pipelines with Apache Airflow running on Amazon MWAA.

On March 13th, 2025, Amazon Web Services announced General Availability of Amazon SageMaker Unified Studio, bringing together AWS machine learning and analytics capabilities.

In today’s data-driven landscape, organizations rely on enterprise applications to manage critical business processes. However, extracting and integrating this data into data warehouses and data lakes can be complex.

Analytics professionals are tasked with integrating data from distributed systems (data lakes, data warehouses, search, NoSQL, machine learning, and more) to create better, secure, and cost-optimized experiences for their customers.

Data silos can create barriers to efficiency and data quality and, as a result, often hinder an organization’s ability to begin their data and ML journeys in the cloud. Manual data ingestion, data preparation, and application integration are time-consuming and expensive.

Data silos are one of the largest challenges to enterprises trying to develop their intelligence capabilities. Manual data integration is time-consuming, expensive, and often unreliable.