Data Analyst Agent

Connect Your Data Source

This example uses BigQuery, but the same setup applies to HubSpot, Airtable, Google Sheets, Postgres, Snowflake, or any other structured system. Open the template. 1. Under Tools, connect the data source where your information lives: 2. BigQuery 3. HubSpot 4. Airtable 5. Google Sheets (Or any database connected to Gumloop)

Let the Agent Explore Your Schema

Before you start asking questions, give the agent context. Ask the agent: “Explore our tables and summarize the database structure so you can efficiently retrieve data in the future.” The agent will: 1. Inspect your datasets 2. Generate a list of tables 3. Outline the schema and relevant fields 4. Write its own instructions for how to query your data 5. Copy the output and paste it into the Instructions section of the agent. This one step dramatically increases speed and accuracy — the agent now knows where everything lives before you ask questions.

Add Additional Tools (Optional)

Web Search: Add Exa Search if you want the agent to pull external sources or competitive context. Image Generation: Add an image-generation flow if you want the agent to output charts, diagrams, or visuals. Slack: Add Slack if you want formatted Block Kit reports sent directly into your team’s channel.