Ctrlk
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Quick Start Tutorial

Your First Analysis

This tutorial walks through all seven steps of the RootCause workflow using sample data. Download the two CSV files below - they represent customer demographics and subscription information for a fictional telecoms company.

Customer Details.csv
160KB
Open
Customer Subscription info.csv
577KB
Open

Step 1: Create a Workspace

Within your organisation create a New workspace. Give the workspace a name and click Create.

Step 2: Connect Data

Go to Sources and click Import data. Select Local File Upload, drag both CSV files onto the drop zone or browse files, and click Upload. RootCause will process the files and begin building the ontology automatically.

Full details: Connect Data

Step 3: Build Ontology

Go to Ontology. The RootCause.ai platform has already scanned the datasets that were uploaded in the previous step and built a semantic map. It automatically identified that Customer Id appears in both files and linked them together. Review the network to confirm the connections look right.

Full details: Build Ontology

Step 4: Build Unified Dataset

Go to Ontology and look at the Recommended Datasets section in the right panel. Click the recommendation the Create dataset to build a joined view of both datasets. RootCause generates the join recipe automatically. You can inspect and edit it in the Operations editor.

Full details: Build Unified Table

Step 5: Build Digital Twin

Within the dataset you want to observe, click Build digital twin on the top right of the page.

Scroll through sections (you don't need to make any adjustments to the setup) :

  1. How do you want to build it?

  2. Choose your data

  3. Add domain knowledge

  4. Review & run

In the builder's final Review & run step, click Discover & train.

This action runs causal discovery and trains the model. Training runs a sequence of stages and takes a few minutes. When it completes you'll see a model fit score.

Full details: Build Digital Twin

Step 6: Digital Twin

When the causal discovery completes, you will see the completed Digital Twin. Click any variable to view more information like explanations, prediction quality, distribution of the data, and causal subgraph.

Step 7: Run Simulations

From your Digital Twin, click the Simulations on the right panel. Try typing a plain-language question into Generate from Query:

Then click Generate Scenario. Review the generated configuration and run it.

The simulation will take a few seconds to complete. Once completed you will see the impact of the Intervention simulation.

Full details: Run Simulations

Step 8: Produce Reports

On the simulation result page that was generated on the previous step, click Export as report located on the top right bar. RootCause.ai produces a structured report with an Executive Summary and evidence-linked findings. Export to PDF to share it.

Full details: Produce Reports

What success looks like

If you followed all eight steps, you now have:

  1. An ontology where Customer Id is linked across both files

  2. A joined Data View built from the Recommended Datasets recommendation

  3. A trained Digital Twin with a model fit score

  4. A Digital Twin you can click into for explanations, prediction quality, data distribution, and causal subgraphs

  5. A simulation run showing the impact of your intervention

  6. An exported PDF report with an Executive Summary and evidence-linked findings

NextConnect Data

Last updated