Sheets Workflows

Sheets Workflows represent the perfect blend of AI agent flexibility and spreadsheet structure. Upload a CSV or Google Sheet with your data, and rtrvr.ai will execute web agent tasks for each row, using other columns as context.

This approach combines the dynamic capabilities of AI agents with the deterministic structure of tables, making complex workflows both powerful and predictable.

How It Works

The system processes your spreadsheet row by row, treating each row as an individual task execution:

Upload your spreadsheet with input data
Define the task using natural language prompts
Specify which columns to use as context
The agent executes the task for each row
Results are written back to new columns

Example Workflow

Consider a lead generation workflow with the following spreadsheet:

csv

Company Name,Website,Industry
  Acme Corp,acme.com,Software
  Beta Inc,beta.io,Healthcare
  Gamma LLC,gamma.co,Finance

With the prompt: "Visit the website and extract the CEO name and company size"

The agent will process each row and return:

csv

Company Name,Website,Industry,CEO Name,Company Size
  Acme Corp,acme.com,Software,John Smith,50-100 employees
  Beta Inc,beta.io,Healthcare,Sarah Johnson,100-500 employees
  Gamma LLC,gamma.co,Finance,Mike Wilson,10-50 employees

Advanced Use Cases

Price monitoring across multiple e-commerce sites
Contact information extraction from company websites
Social media profile analysis and data collection
Competitive research and market analysis
Form submissions with personalized data
Content scraping with structured output

Best Practices

Keep your prompts specific and include examples of expected output format for best results.

Use clear column headers that describe the data
Include example rows to guide the agent
Break complex tasks into smaller, focused workflows
Test with a small subset before processing large datasets
Use rate limiting for respectful web scraping