Available Tools

Fetch the 50 most popular pages for a given environment and time period.

Executes an insight query and returns results. Works with SQL, semantic, segmentation, and funnel insights. For large results, summarize key findings rather than echoing raw data.

Retrieves discovery metadata by its slug. Returns discovery information including title, description, reasoning, status, last review, data_type, and tags. Does NOT execute chart queries - use view_insight for that.

Retrieves a dashboard by its slug. Returns title, description, tags, and ordered widgets (chart/text/section with grid positions). Includes a flat list of referenced insight slugs. Does NOT execute queries — use view_insight for that.

Validates whether a SQL statement is valid DuckDB dialect

Updates an existing insight discovery by its slug. Allows modifying title, description, and insight-specific definitions and parameters. Supports semantic, segmentation, funnel, and SQL insights. Only provide the fields you want to update; omitted fields will remain unchanged.

Update the status of a discovery

Suggest quick replies the user could rely on to accept, reject or discuss the discovery further.

Starts a discovery plan action, transitioning it from pending to running.

Find relevant Altertable agent skills for a task using semantic similarity. Returns the best-matching skills plus guidance on when to use them. Call this before starting work when you need to discover applicable agent capabilities.

Search for memories with relevance-based ranking (considers recency, access patterns, and importance). Supports both semantic (vector) and keyword search. Note: Each search increments access_count on returned memories. Tip: Use this tool proactively at the start of a workflow to auto-recall relevant context.

Search the Altertable platform documentation for information about features, insight types, usage and best practices. Returns relevant documentation snippets with titles, content, and URLs.

Executes one or more SQL queries directly against the lakehouse database using DuckLake dialect. Returns query results as structured data with rows and column metadata.

Previews the results of a SQL query without creating a permanent insight. Useful for testing and validating queries before creating an insight. Returns the query results directly.

Previews the results of a semantic insight without creating a permanent insight. Useful for testing semantic definitions before creating an insight. Returns the semantic query results directly.

Previews the results of a segmentation insight without creating a permanent insight. Useful for testing segmentation configurations before creating an insight. Returns the segmentation analysis results directly.

Previews the results of a retention insight without creating a permanent insight. Useful for testing retention configurations before committing to creation. Returns the retention analysis results directly.

Previews the results of a funnel insight without creating a permanent insight. Useful for testing funnel configurations before committing to creation. Returns the funnel analysis results directly.

Retrieves user traits (attributes) data. Returns user attribute data that can be used for segmentation, personalization, and analysis. User traits include properties like email, name, subscription tier, and custom attributes.

Retrieves available semantic models (sources) for the organization. Semantic models define data structures that can be queried using semantic insights. Optionally filters by connection slug to show models for a specific database connection. Returns model definitions with slugs, fully qualified table names, and schema definitions.

Lists all insights (charts) in the organization. Insights are saved queries that can be SQL, semantic, segmentation, or funnel type. Supports optional query filtering to search by title or description. Returns insight metadata including slug, title, description, chart kind, and creation/update timestamps.

Retrieves events along with statistics for a given time period. Returns aggregated event data including event names, counts, and metadata. Supports optional query filtering to search specific events.

Lists all visible discoveries in the organization. Supports filtering by query (title/description), status, and date range. Returns discovery metadata including slug, title, description, status (pending_review, accepted, rejected, ignored, in_progress, admin_rejected), and timestamps.

Lists all data connections available in the current environment. Returns basic metadata: slug (unique identifier to use with get_connection), name (human-readable), and database engine type. To get detailed schema, tables, and columns for a connection, use get_connection with the slug.

Retrieves organization and environment information for the current session. Use this tool to get context about the organization and environment you are working with.

Returns detailed schema information for a specific connection: database schemas, tables, columns, and semantic models. Use list_connections first to get available connection slugs.

Analyzes a DuckLake SQL query and returns execution plan information including table scan estimates and file statistics. Use this to understand query performance characteristics before execution.

Create a watcher to automatically monitor charts or dashboards on a recurring schedule.

Creates a discovery containing a SQL-based insight visible in the UI for end-user dashboards. Executes custom SQL queries using DuckDB dialect. Use for user-facing custom analytics and dashboard visualizations. Returns the discovery ID and slug.

Creates a new SQL-based insight. Returns the insight ID and slug.

Creates a discovery containing a semantic insight visible in the UI for end-user dashboards. Queries structured data models using semantic definitions. Use for user-facing model-based analytics and visualizations. Returns the discovery ID and slug.

Creates a new semantic model-based insight. Returns the insight ID and slug.

Creates a discovery containing a segmentation insight visible in the UI for end-user dashboards. Segments users into groups based on behavioral patterns and event definitions. Use for user-facing cohort analysis and dashboard visualizations. Returns the discovery ID and slug.

Creates a new segmentation insight. Returns the insight ID and slug.

Creates a discovery containing a retention insight visible in the UI for end-user dashboards. Analyzes user retention by tracking when users return after an initial event. Use for user-facing analytics and dashboard visualizations. Returns the discovery ID and slug.

Store insights, learnings, and procedures discovered during data analysis. Use episodic for analysis sessions/findings, semantic for data facts/patterns, procedural for query techniques/workflows. Higher importance decays slower.

Creates a text-based FYI discovery with markdown/plain text content. Use this for sharing findings, notes, or information that does not require chart visualization. Ideal for text-based insights, recommendations, or explanations. Returns the discovery ID and slug.

Creates a discovery containing a funnel insight visible in the UI for end-user dashboards. Tracks user progression through event sequences to analyze conversion rates and drop-offs. Use for user-facing analytics and dashboard visualizations. Returns the discovery ID and slug.

Creates a new funnel insight. Returns the insight ID and slug.

Creates a plan with actions on an existing discovery. Errors if the discovery already has a plan — use view_discovery to check first. Returns the plan ID and action IDs.

Completes or fails a running discovery plan action.