Spotter APIs

Table of Contents

Supported API operations
Locale settings for API requests
Per-user API rate limits
Additional resources

The Spotter APIs support natural-language-driven analytics, context-aware and guided data analysis, and integration with agentic systems.

The key capabilities of the Spotter APIs include the following:

Initiating and managing conversational sessions
Processing natural-language queries and interpreting user intent
Generating analytical responses, insights, and visualizations
Decomposing complex user queries

Spotter manages conversation sessions, context tracking, and response generation for user-submitted queries. The Spotter APIs are designed for use in Spotter-driven analytics and also for agentic interactions within an orchestrated agent framework.

Spotter API operations require CAN_USE_SPOTTER privilege and at least view-level access to the underlying metadata entities referenced in the response.

Supported API operations🔗

For information about supported API operations, see the following pages:

Locale settings for API requests🔗

When using the Single Answer and Send message APIs, the locale used for API requests depends on your application’s locale settings:

If your application is set to "Use browser language", the API will use this locale to generate responses. To override this setting, you must explicitly include the desired locale code in the Accept-Language header of your API request. To ensure consistent localization, set the Accept-Language header in your API requests when relying on browser language detection, or configure the locale explicitly in the user profile settings in ThoughtSpot.
If you have set a specific locale in your ThoughtSpot instance or user profile, the API will use this locale to generate responses, overriding the browser or OS locale.

Per-user API rate limits🔗

The following rate limits apply to Spotter agent APIs per user:

A maximum of 10 conversation creation requests per minute.
A maximum of 30 query messages to a conversation session per minute.

API endpoint	Rate Limit (per user, per minute)
`/api/rest/2.0/ai/agent/conversation/create`	10
`/api/rest/2.0/ai/agent/conversation/{conversation_identifier}/send`	30
`POST /api/rest/2.0/ai/agent/conversation/{conversation_identifier}/send/stream`	30
`/api/rest/2.0/ai/agent/{conversation_identifier}/converse` Deprecated	30
`/api/rest/2.0/ai/agent/converse/sse` Deprecated	30

If you are integrating these APIs in your environment, consider implementing a retry logic to handle the rate limit errors.

Additional resources🔗

Visit the REST API v2.0 Playground to view the API endpoints and verify the request and response workflows.
For information about embedding Spotter in your app, see Embed Spotter.
For information about MCP server, see MCP server integration.