Snowflake Announces Public Preview of Cortex Agents, a New Class of AI Agents
Snowflake, a leading cloud-based data platform, has announced the public preview of Cortex Agents, a new class of AI agents that can perform a range of business tasks using structured and unstructured data. The company has also announced that, thanks to Anthropic’s latest Claude 3.5 Sonnet model, Cortex Agents are turning in best-in-class agent performance.
The Importance of Data Foundation for AI
According to Snowflake’s SVP of Product, Christian Kleinerman, "We believe that a strong data foundation is important for AI. I have access to a great model. But if I don’t have my data in order, if I don’t know governance, if I don’t know what data sets I have, it is difficult to get value out of AI."
Cortex Agents: A New Class of AI Agents
Cortex Agents are a new class of generative AI applications that are designed to function like human workers. They can automate multi-step, data-intensive tasks, such as accessing structured and unstructured data, running complex queries, and serving the data back to users.
Two Cortex Agents: Cortex Analyst and Cortex Search
There are currently two Cortex Agents: Cortex Analyst, which is based on Anthropic’s latest Claude model, provides text-to-SQL conversion and is designed for working with structured data, such as database table and views; and Cortex Search, which is based on Snowflake’s Arctic AI models, is designed for answering questions on unstructured data, such as PDF or .txt documents.
How Cortex Agents Work
When called via a REST API, Cortex Agents securely kick off a four-part workflow that involves:
- Understanding the request and planning out the specific subtasks
- Executing the tasks via Cortex Analyst, Cortex Search, or SQL generation from natural language
- Evaluating the effectiveness of the answer and determining whether it meets accuracy requirements
- Monitoring and iterating on the workflow to refine behavior for continuous improvement
Security and Privacy
Security and privacy are key aspects of Snowflake’s AI strategy. By registering data within Snowflake’s Horizon Catalog, customers can control access to both structured and unstructured data sets using Horizon’s role-based access control (RBAC) capabilities.
Conclusion
Snowflake’s Cortex Agents are poised to have a significant impact on customer operations, according to Baris Gultekin, head of AI at Snowflake. "At Snowflake, we believe that AI agents will soon be essential to the enterprise workforce. They’ll enhance the productivity for many teams such as customer support analytics, engineering, and they’ll free up employee time to focus on higher value things."
FAQs
Q: What are Cortex Agents?
A: Cortex Agents are a new class of AI agents that can perform a range of business tasks using structured and unstructured data.
Q: What are the two Cortex Agents currently available?
A: The two Cortex Agents currently available are Cortex Analyst and Cortex Search.
Q: How do Cortex Agents work?
A: Cortex Agents work by understanding the request, planning out the specific subtasks, executing the tasks, evaluating the effectiveness of the answer, and monitoring and iterating on the workflow.
Q: What is the benefit of using Cortex Agents?
A: The benefit of using Cortex Agents is that they can automate multi-step, data-intensive tasks, freeing up employee time to focus on higher-value tasks.
