Configuring capabilities

Capabilities are optional features that extend your AI Agent's functionality or modify its behavior. Enable only the capabilities your use case requires to maintain optimal performance and security.

Available capabilities

Query sources for insights

Enables your Agent to generate and execute SQL queries directly against your data connections, providing dynamic analysis beyond pre-configured widgets and layers.

What this capability unlocks

This capability grants access to powerful data manipulation tools:

Tool	Purpose
execute_query	Run AI-generated SQL queries to analyze data and return insights conversationally.
add_source	Create temporary data sources from SQL queries that can be visualized as map layers.
remove_source	Clean up temporary AI-generated data sources.

Pair this capability with a semantic model. When the Agent generates SQL, the model tells it what your metrics mean, which keys to join on, and how your spatial data is structured, which makes the generated queries far more reliable.

Important limitations for public maps: Maps containing AI Agents with Query Sources for insights capability cannot be made public. This is a security restriction to prevent unauthorized data access. For public-facing applications:

• Build required logic into Workflows and exposed them as MCP Tools.

• Use pre-configured widgets and layers.

• Consider creating a separate, limited connection for public access.

Security considerations: This capability allows direct database access through AI-generated SQL. Enable only when:

• Users are authorized to access the underlying data

• Your connection has appropriate read-only permissions

• You've configured proper data access policies in your organization