AI is only as good as the data it runs on. With data spread across multiple platforms, it’s a challenge to ensure quality and security. As the first Iceberg-based OneLake integration partner, we’re enabling seamless, bidirectional data access between Snowflake and Microsoft Fabric. Join this session to see how the Onelake integration and Snowflake’s robust features for the Microsoft ecosystem unlock endless possibilities, from building better AI to developing powerful business applications.

Talk by Celeste Hogan, Developer Advocate at Snowflake.

Kafka and Flink tend to get lumped in as "data services", in the sense that they process data, but in comparison to traditional databases they differ quite dramatically in functionality and utility. In this talk, we'll run through the lifetime of a write in Postgres to establish a baseline, understanding all the different services that data hits on its way down to the disk. Then we'll walk through writing data to a Kafka topic, and what 'writing' (or really, streaming) data to a Flink workflow looks like from a similar systems perspective. Along the way, we'll understand the key differences between the services and why some are more suited to long-term data storage than others.

Come see how dbt empowers teams to harness Apache Iceberg and Snowflake Open Catalog for reliable, scalable, and agile analytics pipelines

The future of AI is here. Join AI and data industry thought leader Ashley Kramer from OpenAI as she shares how AI-powered development and intelligent systems act as force multipliers for organizations—and how to confidently embrace these accelerants at scale. In the second half of the keynote, she'll be joined by a panel of product leaders from across the data stack for a discussion on the future of analytics in an AI-driven world and how dbt and ecosystem partners are innovating to rewrite what’s possible: turning yesterday's science fiction into today's reality. For our Coalesce Online attendees, join us on Slack in #coalesce-2025 to stay connected during keynote!

Change – social and environmental, rural and urban – disproportionately impacts women and children. The UN reports that 80% of people displaced by climate change are women and girls. Research shows that domestic violence and crime, particularly against women, increases with male job loss. Understanding prevailing patterns by combining location data with social and environmental data can help identify vulnerable populations and mitigate these risks.

Join this session with Snowflake and Ordnance Survey to:

• Explore how integrating different types of geospatial data, such as maps, with open source data can expose the impact of these changes

• Discover how overlaying this information enriches visualization and analysis of vulnerabilities to identify better solutions

• Learn how data from the UK’s Ordnance Survey available through the Snowflake Marketplace addresses global challenges and helps mitigate risks

• Hear about Snowflake’s initiative to End Data Disparity

In the scramble for agentic systems, the question has to be asked, are we ready? 

This session highlights the common challenges and complexities we face during the rush for autonomous orchestration. We'll demonstrate how Snowflake's AI data platform offers a unified, adaptable, and trusted solution for creating data agents you can trust.

This 60-minute workshop walks through how to design, deploy, and evaluate multi-agent systems using Snowflake Cortex. You’ll build agents that connect to enterprise data sources (structured and unstructured) and perform intelligent, multi-step operations with Cortex Analyst and Cortex Search. The session also focuses on reliability, instrumenting agents with inline, reference-free evaluation to measure goal progress, detect failure modes, and adapt plans dynamically using trace-based observability tools like TruLens and Cortex eval APIs. By the end of the workshop, you’ll have a repeatable framework for deploying trustworthy agentic systems in production and be able to answer complex queries across multiple data sources.

This 60-minute workshop walks through how to design, deploy, and evaluate multi-agent systems using Snowflake Cortex. You’ll build agents that connect to enterprise data sources (structured and unstructured) and perform intelligent, multi-step operations with Cortex Analyst and Cortex Search. Then we’ll go beyond functionality and focus on reliability. You’ll learn how to instrument your agent with inline, reference-free evaluation to measure goal progress, detect failure modes, and adapt plans dynamically. Using trace-based observability tools like TruLens and Cortex eval APIs, we’ll show how to identify inefficiencies and refine agent behavior iteratively.

As enterprise AI adoption accelerates, data agents that can plan, retrieve, reason, and act across structured and unstructured sources are becoming foundational. But building agents that work is no longer enough, you need to build agents you can trust. This 60-minute workshop walks through how to design, deploy, and evaluate multi-agent systems using Snowflake Cortex. You’ll build agents that connect to enterprise data sources (structured and unstructured) and perform intelligent, multi-step operations with Cortex Analyst and Cortex Search. Then we’ll go beyond functionality and focus on reliability. You’ll learn how to instrument your agent with inline, reference-free evaluation to measure goal progress, detect failure modes, and adapt plans dynamically. Using trace-based observability tools like TruLens and Cortex eval APIs, we’ll show how to identify inefficiencies and refine agent behavior iteratively. By the end of this workshop, you’ll: - Build a data agent capable of answering complex queries across multiple data sources - Integrate inline evaluation to guide and assess agent behavior in real time - Debug and optimize execution flows using trace-level observability - Leave with a repeatable framework for deploying trustworthy agentic systems in production

60-minute workshop walks through how to design, deploy, and evaluate multi-agent systems using Snowflake Cortex. You’ll build agents that connect to enterprise data sources (structured and unstructured) and perform intelligent, multi-step operations with Cortex Analyst and Cortex Search. Then we’ll focus on reliability, instrument your agent with inline, reference-free evaluation to measure goal progress, detect failure modes, and adapt plans dynamically using trace-based observability tools like TruLens and Cortex eval APIs to identify inefficiencies and refine agent behavior iteratively. By the end of this workshop, you’ll have a repeatable framework for deploying trustworthy agentic systems in production.

We are presently in the midst of an artificial intelligence (AI) revolution, where advances in deep learning technologies are rewriting the rules of entire industries – including how we forecast the weather and predict changes in our climate. In this session we will learn how the Met Office is successfully navigating the opportunities and challenges (both technological and cultural) of embedding AI across the organisation, and discuss how the complementary use of AI alongside traditional physics-based weather and climate models will further help people make better decisions to stay safe and thrive.

Discover how to efficiently scale AI solutions while maintaining security and cost efficiency. Learn about integrating LLMs, intelligent search, and automated tuning into your business workflows to optimise performance and impact.

This talk shares Polidea’s journey from mobile app development studio to an OSS oriented business partner. We will tell you our story towards code leadership throughout the years. We are also going to share the challenges and practical insights into managing open source projects in our company. After this talk, you will know how we approached combining open source, business and team management not forgetting about a human aspect. This is a sponsored talk, presented by Polidea .

Tanmaiyii will be exploring Responsible AI and focusing on how it impacts women and people from diverse backgrounds.

Talk about evaluating AI agents.