Skip to main content

Analyzing data in Workflows

Automate data analysis and file manipulation with AI-powered insights

Jake Rosenthal avatar
Written by Jake Rosenthal
Updated over a week ago

Data Analysis Mode in Cassidy Workflows enables you to automatically analyze, manipulate, and generate insights from structured data files like CSVs, Excel spreadsheets, PowerPoint presentations, Word documents, and PDFs. When enabled, this powerful feature allows the AI to write code on-the-fly to perform complex data operations, create visualizations, and make direct edits to files—all without requiring technical expertise.

This capability is particularly useful for tasks like analyzing sales data exports to uncover trends, generating formatted monthly reports with charts and graphs, editing custom presentation templates with AI-generated content, and transforming raw data into polished, branded deliverables.

We'll walk through a complete example that demonstrates Data Analysis Mode in action: uploading a sales data spreadsheet, analyzing it to create insights and visualizations, and then combining those results into a comprehensive report.

Step-by-step example: Sales data analysis to report

  1. Set up a file upload trigger: Create a Workflow with a Manual Trigger that accepts file uploads. Add a file input field to allow users to upload Excel or CSV files containing sales data.

    For more information on Manual Triggers, see the Manual Trigger article.

  2. Add a Generate Text action: Click the plus button to add a new action and select "Generate Text". This will analyze your uploaded sales data file or data passed from previous steps.

  3. Configure the analysis prompt: In the prompt field, reference the uploaded file from your trigger or data output from a previous step: "Analyze the attached sales data and provide key insights including trends over time, top performing products, and revenue patterns. Create a summary of findings with specific metrics. In addition, generate a chart visualization showing sales performance trends by month."

    You can reference files from trigger attachments or data outputs from previous Workflow steps, allowing you to chain multiple data processing actions together.

  4. Enable Data Analysis Mode: In the "Advanced Model Settings" tab, toggle on "Data Analysis Mode". This allows the AI to write code to analyze your data and create a chart showing sales trends over time.

    When Data Analysis Mode is enabled, the AI can manipulate structured files and data, performing operations like data filtering, aggregation, and visualization generation.

  5. Add a second Generate Text action: Click the plus button to add another "Generate Text" action that will create a comprehensive report using the analysis from step 4.

  6. Configure PowerPoint generation: Reference the output from your first analysis step and prompt the AI to create a PowerPoint presentation: "Using the analysis results and chart referenced, create a professional PowerPoint presentation with the key findings, chart visualizations, and executive summary slides."

    When Data Analysis Mode is enabled on an action, you'll see a "Generated Files" variable in the outputs that contains any files created during processing. Make sure to reference this variable when passing files between steps.

  7. Enable Data Analysis Mode for PowerPoint creation: Toggle on "Data Analysis Mode" for this step as well, allowing the AI to create and format the PowerPoint presentation with the analysis results and visualizations.

  8. Run and review: Execute the Workflow by uploading a sales data file. The AI will analyze the data in the first step, then use those results to generate a comprehensive PowerPoint presentation in the second step. Any files created during the process will have download options available in the results panel.

Understanding the results

When your Workflow completes, you'll be able to see detailed information about what Data Analysis Mode accomplished:

  • View the analysis and code: Click the "Analyzed sources" dropdown in the results panel, then click the code icon (</>) next to any analysis step to open a modal showing the actual Python code the AI wrote to process your data

  • Download generated files: Any files created during the analysis (charts, presentations, reports) will appear with download buttons in the results panel

  • Review the output: The generated PowerPoint presentation will include professional slides with your data insights, key metrics, trend analysis, and embedded visualizations

The output will be detailed analysis and professional reporting, with the ability to download any generated files, charts, or formatted documents directly from the Workflow results.

Did this answer your question?