Usage Examples

Usage Examples

These examples show real conversations you can have with Claude once the CorralData integration is connected.

Example 1: Explore your data and run a query

Goal: Understand your database schema and query it for insights.

You: What schemas and tables do I have available?

Claude will call list_schemas and list_tables to discover your data model, then present a summary.

You: Describe the orders and customers tables

Claude calls describe_tables to retrieve column names, types, and relationships for both tables at once.

You: How are those two tables related?

Claude calls get_relationships filtered to those tables and shows the foreign key connections.

You: Write a query to show total revenue by customer for the last 30 days, ordered by highest revenue first

Claude uses the schema context to write accurate SQL and executes it with execute_sql, returning the results in a table.

---

Example 2: Build a dashboard from scratch

Goal: Create a new board with widgets to visualize key metrics.

You: Create a new board called "Sales Overview"

Claude calls create_board and returns the new board with its URL.

You: Add a KPI widget showing total revenue this month

Claude writes the SQL query, validates it with validate_widget_query, then calls create_widget with the appropriate chart type and configuration.

You: Now add a bar chart showing revenue by product category

Claude creates another widget with a bar chart type, placing it below the KPI.

You: Add a date filter to the board so users can change the time range

Claude calls create_board_filter to add an interactive date filter that connects to the widgets.

---

Example 3: Analyze and improve an existing dashboard

Goal: Review what's on an existing board and make changes.

You: Show me all my boards

Claude calls list_boards and presents a summary with names and URLs.

You: What widgets are on the "Marketing Metrics" board?

Claude calls get_board with details enabled, then list_widgets for that board to show all widgets with their types and queries.

You: The "Conversion Rate" widget looks wrong. Show me its query

Claude calls get_widget to retrieve the full widget configuration including its SQL query.

You: Fix the query to exclude internal traffic by filtering out email addresses ending in @corraldata.com

Claude updates the SQL, validates it with validate_widget_query, then calls update_widget to save the fix.

---

Example 4: Schema discovery for a new project

Goal: Quickly understand an unfamiliar database to start building reports.

You: I need to build reports on our HR data. Search for any tables related to employees or payroll

Claude calls search_tables with relevant keywords and returns matching tables across all schemas.

You: Describe those tables in detail — I need to understand the columns and data types

Claude calls describe_tables for all matched tables, showing columns, types, primary keys, and foreign key relationships.

You: What are the possible values in the employment_status column?

Claude calls get_column_values to retrieve the distinct values, helping you write accurate filter conditions.

You: Now write a query to show headcount by department and employment status

Claude uses the discovered schema to write and execute the query with execute_sql.