Skip to main content
Depending on your use case, analysis can be as simple as a single visualization or as complex as a dashboard with multiple interactive components. This page walks you through using the Agent to create a simple analysis and then building a more complex dashboard from that starting point.

​
Objectives

In this tutorial, you will:
  • Add source data to the pipeline.
  • Ask the Agent to create a pipeline that produces a specific visualization.
  • Prompt the Agent to add a visualization to a new analysis.
  • Embed a pipeline parameter in the generated pipeline.
  • Update the analysis dashboard to include interactive components.
  • Run the analysis from the end user perspective.

​
Prerequisites

To complete this tutorial, you will need Prophecy 4.2.5 or later.

​
Create the pipeline

You’ll start with a sample dataset that contains information about home technology sales transactions. Then, you will prompt the Agent to create a pipeline that results in an insight about the data.

​
Add source data

  1. Open the Source/Target gem category.
  2. Click Table. This adds a new Table gem to the canvas.
  3. Hover over the gem and click Open.
  4. Select + New Table.
  5. For Type and Format, choose Seed.
  6. Name the seed home_tech_transactions.
  7. For the Seed path, choose seeds. Prophecy saves your seed file in this folder of the project repository.
  8. Click Next.
  9. In the Properties tab, paste the following data. 
    Date,Transaction_ID,Product_Category,Region,Units_Sold,Unit_Price,Discount_Applied
2026-01-01,TXN1001,Smart Speakers,North,5,120.00,0.10
2026-01-01,TXN1002,Security Cameras,West,2,250.00,0.00
2026-01-02,TXN1003,Smart Lighting,East,12,25.00,0.05
2026-01-02,TXN1004,Smart Speakers,South,3,120.00,0.00
2026-01-03,TXN1005,Thermostats,North,8,180.00,0.15
2026-01-03,TXN1006,Security Cameras,East,4,250.00,0.10
2026-01-04,TXN1007,Smart Lighting,West,20,25.00,0.20
2026-01-04,TXN1008,Smart Speakers,North,2,120.00,0.00
2026-01-05,TXN1009,Thermostats,South,5,180.00,0.00
2026-01-05,TXN1010,Security Cameras,West,1,250.00,0.05
2026-01-06,TXN1011,Smart Lighting,North,15,25.00,0.00
2026-01-06,TXN1012,Smart Speakers,East,6,120.00,0.10
2026-01-07,TXN1013,Thermostats,West,3,180.00,0.10
2026-01-07,TXN1014,Security Cameras,South,2,250.00,0.00
2026-01-08,TXN1015,Smart Lighting,East,25,25.00,0.15
2026-01-08,TXN1016,Smart Speakers,North,4,120.00,0.00
2026-01-09,TXN1017,Thermostats,North,6,180.00,0.05
2026-01-09,TXN1018,Security Cameras,West,3,250.00,0.00
2026-01-10,TXN1019,Smart Lighting,South,10,25.00,0.00
2026-01-10,TXN1020,Smart Speakers,East,8,120.00,0.20
2026-01-11,TXN1021,Thermostats,East,4,180.00,0.00
2026-01-11,TXN1022,Security Cameras,North,2,250.00,0.10
2026-01-12,TXN1023,Smart Lighting,West,30,25.00,0.10
2026-01-12,TXN1024,Smart Speakers,South,5,120.00,0.00
2026-01-13,TXN1025,Thermostats,West,7,180.00,0.15
2026-01-13,TXN1026,Security Cameras,East,3,250.00,0.00
2026-01-14,TXN1027,Smart Lighting,North,12,25.00,0.05
2026-01-14,TXN1028,Smart Speakers,West,4,120.00,0.00
2026-01-15,TXN1029,Thermostats,South,6,180.00,0.10
  10. Click Next.
  11. Click Load Data to preview the data in tabular format.
  12. Click Save.

​
Generate transformation logic

In the Chat interface, ask the Agent to create a pipeline that results in a bar chart showing the total sales by product category. 
Visualize sales performance per product category in @home_tech_transactions
The Agent:
  • Transforms the data to aggregate the total sales by product category.
  • Creates a bar chart visualization of the data.
  • Adds a Visualize gem to the canvas.
  • Create a new analysis that links to the pipeline.
  • Includes the bar chart which uses input data from the Visualize gem.
Send Agent prompt At this point, you will already have a pipeline and a baseline analysis dashboard. You can keep asking the Agent to transform the data to answer different questions, or you can continue to build on the analysis yourself. When you switch between the pipeline tab and the analysis tab, the same Agent session remains open.
If you would like to create an analysis without the Agent, you have two options:
  • Hover over the pipeline in the project browser and select the Create analysis icon.
  • Click the + plus icon in the canvas header and select Create analysis.
Create analysis icon

​
Add interactive components

To add interactive components to the analysis, you’ll need to embed a pipeline parameter in the pipeline. Pipeline parameters enable dynamic behavior in pipelines by allowing values to be set at runtime. In this case, pipeline parameter values are set by the end user when they run the analysis.

​
Create a pipeline parameter

In this section, you’ll define a pipeline parameter called region. The parameter will capture the region that the user selects, allowing the pipeline to filter transactions based on the region the user wants to see.
  1. Open the pipeline tied to the analysis.
  2. Click default in the project header to open the parameter settings.
  3. Open the Pipeline Parameters tab.
  4. In the default parameter set, click + Add Parameter.
  5. Name the parameter region.
  6. Set the parameter type to String.
  7. Click Select expression > Value.
  8. Enter North as the default value to be used during interactive pipeline runs.
  9. Click Save.

​
Add a filter

Next, add a Filter gem to the pipeline. To make the filter condition dynamic, you’ll use the pipeline parameter in the gem.
  1. Add a Filter gem directly after the Source gem and before the next gem (generated by the Agent).
  2. Open the Filter gem configuration.
  3. For the filter condition:
    • Click Select expression > Column and select the Region column.
    • Click Select operator and select equals.
    • Click Select expression > Configuration Variable and select the region parameter.
    Configure visual expression to use parameter
    This expression is equivalent to Region = {{ var('region') }} in the Code view.
  4. Click Save.

​
Add a Text Input component

Add a Text Input component to allow the end user to enter the region they want to see.
  1. Open the analysis dashboard that the Agent created.
  2. Click Edit.
  3. Open the Interactive dropdown and select Text Input.
  4. In the Inspect tab, for the Configuration field, select the region parameter.
  5. For the Label, enter Region.
  6. Drag the Text Input component above the bar chart visualization.

​
Run the analysis

Let’s return to the analysis preview so we can test the new component.
  1. From the analysis, click Back to Preview.
  2. In the Region field, enter West.
  3. Click the Run button.
  4. Review the bar chart to see the total sales by product category for the West region.
When the analysis runs, Prophecy always executes the entire underlying pipeline. This means any additional transformations, tables, or other components included in the pipeline will also run, even if they’re not exposed in the dashboard. Be mindful of how you design the pipeline to ensure your dashboard triggers only the intended logic.

​
Share the dashboard

Access to analyses is controlled by Prophecy’s team-based permission model. If your team owns a project, you have full edit access. This means that you can build, edit, and delete analyses in the project. If a project is shared with your team, you cannot edit any pipeline’s or analysis’s structure. However, you can run analyses from the shared project. This ensures that your data engineering team can share pipelines they developed without exposing them to changes.
To learn more, reference the documentation on team-based access.

​
What’s next

To address your specific business requirements, leverage more complex components to construct robust analysis dashboards. To learn about the end user experience, see consume analyses.