Part II Select AI Agent Framework

Part II builds on the Select AI capabilities introduced in Part I. While Part I describes how Select AI uses natural language to generate and run SQL queries, use retrieval-augmented generation (RAG), and interact with database data, Part II introduces Select AI Agent Framework, an autonomous agent framework that extends these capabilities for multi-step and multi-turn workflows.

Select AI Agent Framework enables you to create interactive and autonomous agents inside Autonomous AI Database. Agents Framework can reason about requests, plan actions, use built-in or custom tools including Natural Language to SQL (NL2SQL) and RAG evaluate results, and retain context across conversations through short-term and long-term memory.

Select AI Agent Framework uses the ReAct (Reasoning and Acting) pattern and supports defining agents, tools, tasks, and teams using SQL and PL/SQL. The DBMS_CLOUD_AI_AGENT package provides the management, orchestration, and security boundaries for these agent workflows.

  • Select AI Agent Framework
    Select AI Agent Framework (autonomous agent framework) enables you to build interactive and autonomous agents inside Autonomous AI Database, combining planning, tool use, reflection, and memory to deliver multi-turn workflows.
  • Select AI Agent Framework Interfaces
    Select AI Agent Framework interfaces support environments such as SQL, PL/SQL, and Python.
  • Select AI Agent Framework Concepts
    Explores the concepts and terms related to Select AI Agent Framework (autonomous agent framework).
  • Select AI Agent Framework Use Cases
    Select AI Agent Framework supports practical scenarios across roles: connect external services, build task-focused automation with PL/SQL tools, and enable conversational access to data using natural-language interactions.
  • Getting Started with Select AI Agent Framework
    To use Select AI Agent Framework, complete the prerequisites and create the agent objects that the framework uses at run time. Select AI Agent Framework provides procedures to create agents, tools, tasks, and teams, and you can run a team either with the Select AI agent framework action or with DBMS_CLOUD_AI_AGENT.RUN_TEAM.
  • Examples of Using Select AI Agent Framework
    Explore examples that show how to build, configure, and interact with Select AI Agent Framework for common tasks such as movie analysis, log analysis and customer support.