Business Intelligence & Reporting

Describe what you want and your AI builds it: dashboards, KPI reports, recurring summaries. No data model setup, no visual editor, no maintenance when schemas change.

From question to dashboard

Break down orders by product category and status, then build me a dashboard.

AI calls get_schema("snowflake-demo-datasource", database="ANALYTICS", table="ORDERS")
   -> 8 columns including ORDER_STATUS, PRODUCT_CATEGORY, ORDER_AMOUNT

AI writes queries/snowflake-demo-datasource/orders_breakdown.sql
AI calls query("snowflake-demo-datasource", "queries/snowflake-demo-datasource/orders_breakdown.sql")
   -> 17 orders across 5 categories, 4 statuses -> cached in DuckDB

AI calls create_data_view with bar chart config
   -> Dashboard created, viewable in web app

AI: Orders breakdown:
    - DELIVERED: 11 orders, $9,833 (72%)
    - SHIPPED: 3 orders, $2,586 (19%)
    - PENDING: 2 orders, $1,195 (9%)
    - CANCELLED: 1 order, $123 (<1%)

    Dashboard is live at your workspace web app.

Add a breakdown by country.

AI updates the query and dashboard
   -> Top countries: USA (4 orders), UK (3), Germany (2)

Dashboards are viewable in the conversation and in the web app. They have shareable URLs.

For Claude Plugin users, this is a meaningful difference from a traditional BI handoff: the dashboard can appear inline in the same chat where Claude explored the schema and wrote the query, so you can refine it in context instead of switching tools.

Recurring reports

Once you've built a useful query or dashboard, save it for reuse:

Save this as a reusable query I can run next month.

AI: Saved to queries/snowflake-demo-datasource/orders_breakdown.sql
    To re-run: "Run the orders breakdown query"

Reports and dashboards persist in your workspace. Query files are already saved by the standard workflow - you can re-run or modify them in any future session.

How real teams use this

HubSpot deal pipeline. A RevOps lead at a gaming company tracks all open deals broken down by stage, with line items, product SKUs, and revenue by deal. They combine HubSpot with Google Sheets and Jira data, running 349 commands across 10 active days to build a comprehensive pipeline view.

Weekly board metrics. An ops team combines Snowflake revenue data with Salesforce pipeline data and generates a weekly summary: new ARR, net retention, pipeline coverage, churn rate.

Spend management. A finance team queries invoices and orders from Snowflake, generates quarterly summaries, and flags orders not yet invoiced. The queries persist in the workspace for monthly re-runs.

Best practices

Dashboards persist. Artifacts from create_data_view are saved to your workspace and viewable through the web app. Share the link with teammates - they don't need to run anything.

Start simple, then layer. Ask for a basic chart first, then add dimensions, filters, or data from other sources.

Ask for the format you need. If you need a chart for a slide deck, say so. A CSV for a spreadsheet? Ask for that. Your AI exports in whatever format is useful.