ModelMonkey for Data Analysts

ModelMonkey transforms how data analysts work by enabling self-service data access through natural language. Instead of writing SQL queries or waiting for data engineering support, you can simply describe the data you need in plain English.

This guide covers the ModelMonkey features most relevant to data analysts:

• Query connected databases without writing SQL
• Enable business users to self-serve on data requests
• Combine data sources by joining spreadsheet data with external databases
• Create visualizations and summaries directly in your spreadsheet

Before you can query external data, you'll need to set up connections to your databases. ModelMonkey supports:

PostgreSQL
Connect to any PostgreSQL database, including Amazon RDS, Google Cloud SQL, Azure Database for PostgreSQL, and self-hosted instances.

Google BigQuery
Connect to BigQuery datasets using a service account for large-scale analytics workloads.

Once connected, you can reference these data sources by name in your requests. For example, if you name your connection "Sales Database," you can say "Pull customer data from the Sales Database."

For detailed setup instructions, see External Data Connections.

With your data sources connected, you can query them using plain English. ModelMonkey translates your requests into SQL and returns the results.

Example Requests

• "Show me sales by region for last month from our PostgreSQL database"
• "Find the top 10 customers by revenue from BigQuery"
• "Pull all orders from the last 7 days and add them to my spreadsheet"
• "How many active users do we have by country?"
• "What's the average order value by product category?"

How It Works

1. Describe the data you need in natural language
2. ModelMonkey generates the appropriate SQL query
3. The query runs against your connected database
4. Results are returned to your spreadsheet or displayed for review

You can also ask follow-up questions to refine your query: "Now filter that to only show regions with more than $100K in sales."

Once you have data in your spreadsheet, ModelMonkey can help you analyze and visualize it:

Create Charts

• "Create a bar chart showing sales by region"
• "Make a line chart of monthly revenue trends"
• "Add a pie chart showing market share by product"

Summarize Data

• "Calculate totals and averages for each column"
• "Summarize this data by category"
• "What are the key insights from this dataset?"

Add Calculations

• "Add a column calculating the percentage change month-over-month"
• "Calculate year-over-year growth for each product"
• "Add a running total column"

Format and Highlight

• "Highlight cells where value exceeds the average"
• "Apply conditional formatting to show top performers in green"
• "Format the revenue column as currency"

One of ModelMonkey's most powerful features is the ability to join data from different sources in a single request:

Join Spreadsheet Data with Databases

• "Match the customer IDs in my spreadsheet with the customer table in our PostgreSQL database"
• "Enrich this list with email addresses from our CRM database"
• "Add company size data from BigQuery to my prospect list"

Cross-Reference Documents
Upload a PDF report and compare it with database data:

• "Compare the quarterly figures in this PDF to our actual numbers in the database"
• "Verify these invoice totals against our orders table"

Aggregate Across Sources

• "Combine web analytics from BigQuery with sales data from PostgreSQL"
• "Create a unified view of customer data from multiple databases"

This eliminates manual data exports and copy-paste workflows, giving you a single source of truth in your spreadsheet.

Use Descriptive Connection Names
Name your database connections clearly (e.g., "Production Analytics," "Marketing Data Warehouse") so you can easily reference them in requests.

Start Small, Then Expand
Begin with simple queries to verify you're getting the right data, then add filters and aggregations. This helps catch issues early.

Specify Time Ranges
Always include date ranges in your requests when dealing with time-series data: "sales for the last 30 days" is more precise than "recent sales."

Save Common Queries
For frequently-used data pulls, keep a reference sheet with example prompts you can copy and modify.

Combine with File Uploads
Upload PDF reports or documents when you need to cross-reference external data with your database. This is especially useful for variance analysis and reconciliation.

Verify Critical Numbers
For important business decisions, spot-check results by comparing a few data points with your source systems.

Ready to dive deeper? Explore these related features:

• External Data Connections — Set up PostgreSQL and BigQuery connections
• SQL Queries — Write custom SQL for advanced use cases
• File Uploads — Upload PDFs for cross-referencing
• Spreadsheet Editing — Learn about all spreadsheet operations

For questions about specific database configurations or advanced query patterns, check the detailed documentation pages linked above.