Autonomous Database Select AI

The image shows how Autonomous Database Select AI works. The diagram outlines how you can have a conversation with your data by asking a natural language question through an interface, such as an integrated development environment or application, via text or voice.

Autonomous Database Select AI then uses a large language model (LLM) to generate a SQL query and performs the following tasks:

• 1) Augments the natural language question with metadata from the schema(s) identified in the user’s profile.
• 2) Feeds the LLM with an augmented prompt.
• 3) LLM produces a SQL query against the database.
• 4) Query is run and the result is sent to the user.
• 5) Previous questions are retained for conversation-like user interactions.

Finally, the user receives a response back with the answer from their own organization’s data, based on its existing data security policy.

This image shows how Autonomous Database Select AI works. The diagram shows how you generate personalized content just by asking a question into the Select AI prompt.

A user kicks off a workflow through an application. For example, the user wants to create a promotional offer based on a customer’s previous purchases.

The application utilizes data in Autonomous Database and creates personalized targeted promotional offers via a large language model (LLM) including these steps:

• 1) Context from Autonomous Database (for example, customer demographic info and purchasing behavior, products that need to be promoted, etc.) is queried.
• 2) Prompt task instructions are combined with this data (for example, recommend similar products from the promoted product list; write a personalized and convincing e-mail with the recommendations)
• 3) It then feeds the LLM with the augmented prompt and processes the result.

The final output is provided to the user that includes a compelling promotional email offer with personalized product recommendations based on customer information, behavior and past purchases.