Snowflake Intelligence is an Enterprise Intelligence Agent that provides every user with the ability to answer complex questions in natural language, and puts insights at every user’s fingertips. With a single question, you can get comprehensive insights across your business data. It moves beyond the “what” to the critical “why” with an always-available thought partner at their fingertips that can facilitate deep research and suggest solutions to previously difficult and time-consuming business problems.

Snowflake Intelligence removes the barriers to insights, enabling users to understand the cross-sections of their data and test assumptions with a shared understanding of the data needed to make impactful business decisions.

Ask complex questions of all your data, analyze and get insights instantly with Snowflake Intelligence as your always-on thought partner.

Cortex Knowledge Extensions (CKEs) allow publishers to bring their documents (news articles, market research reports, books, articles, etc.) directly to customers in their generative AI applications. They are Snowflake Cortex Search Services that can be shared on the Snowflake Marketplace or through private listings. They enable a retrieval-augmented generation (RAG) architecture to integrate licensed and proprietary content into Cortex AI applications.

Download the Git repository. This is how you get the necessary source code and data to complete this quickstart.

How to acquire external knowledge sources from the Snowflake Marketplace and create the building blocks (agents) for Snowflake Intelligence that can respond to questions by reasoning over data from Cortex Knowledge Extensions.

An Enterprise Intelligence Agent - Snowflake Intelligence - that can respond to questions by reasoning over data from Cortex Knowledge Extensions.

An agent is an intelligent entity within Snowflake Intelligence that acts on behalf of the user. Agents are configured with specific tools and orchestration logic to answer questions and perform tasks on top of your data.

Note that you can create multiple agents for various use cases and/or business teams in your organization.

Add the following starter questions under Example questions:

Tools are the capabilities an agent can use to accomplish a task. Think of them as the agent's skillset and note that you can add one or more of each of the following tools.

Your Agent is now deployed and connected to the external documentation! Open Snowflake Intelligence and make sure you're signed into the right account. If you're not sure, click on your name in the bottom left >> Sign out and sign back in. Also note that your role should be set to SNOWFLAKE_INTELLIGENCE_ADMIN and your agent should be set to Snowflake_Documentation.

Now, let's ask the following questions.

NOTE: The Agent will use the Send_Email custom tool to summarize the answer and send the content to the verified email address configured in the tool. Check your inbox to see the summary email that would have been sent to the email address set in AI & ML >> Agents >> Snowflake_Documentation >> Custom tools >> Send_Email >> recipient_email >> Description.

Congratulations! You've successfully built an enterprise intelligence agent - Snowflake Intelligence - that can respond to questions by reasoning over the data from Cortex Knowledge Extensions. You have expanded your application’s reach beyond your organization’s internal data.

You've learned how to create the fundamental building blocks for Snowflake Intelligence that can reason effectively over the data from Cortex Knowledge Extensions.