Building Agentic Application with Anthropic in Snowflake
Harke Harkema
Senior Solution Engineer, Snowflake
Join Snowflake on the AI Developer Track on Day 2 (25th) at 14:30pm. Learn how to design and deploy intelligent data agents using Snowflake Cortex. These agents are capable of orchestrating complex, multi-step operations by retrieving and reasoning over both structured and unstructured data using Cortex Analyst and Cortex Search.
In this session, you’ll learn how to build a Data Agent using Snowflake Cortex AI that can intelligently respond to questions by reasoning over both structured and unstructured data.
We’ll use a custom dataset focused on bikes and skis. This dataset is intentionally artificial, ensuring that no external LLM has prior knowledge of it. This gives us a clean and controlled environment to test and evaluate our data agent. By the end of the session, you’ll have a working AI-powered agent capable of understanding and retrieving insights across diverse data types — all securely within Snowflake.
What You Will Learn
- How to setup your environment using Git integration and Snowflake Notebooks
- How to work with semantic models and setup Cortex Analyst for structured data
- How to setup Cortext Search for unstructured data like PDFs and images
- How to use Cortex Agents REST API that uses these tools in a Streamlit application
- What You Will Build
- A Data Agent packaged in a Streamlit application that can intelligently respond to questions by reasoning over both structured and unstructured data.
What You Will Need
To complete this lab, you’ll need to create a Snowflake account.
- Click on this link to create a free trial account.
- Complete the first page of the form on the page.
- On the next section of the form, be sure to set the Snowflake edition to Enterprise (Most popular).
- Select AWS – Amazon Web Services as the cloud provider.
- Select US West (Oregon) as the region.
- Complete the rest of the form and click Get started.
SESSION
Snowflake Workshop: Building Agentic Application with Anthropic
AI Developer Conference stage
14:30 - 16:00