# Quick Start Tutorial

{% hint style="info" %}
If you want to get started quickly, demo datasets are provided below in two sample CSV files. They represent customer demographic information and customer subscription information for a fake telecommunications company.
{% endhint %}

{% file src="/files/oOa9U6C1e7nwpYruDlSZ" %}

{% file src="/files/KEiTi6YXSMtM3ycDnXWv" %}

### **Step 1: Upload Data**

Go to **Data** → **Datasets** and upload a CSV file or connect a data source. Even a single spreadsheet is enough to get started. See [Uploading Datasets](/more-details/data-management/uploading-datasets.md).

<figure><img src="/files/R19UCGzxeqi0ssR5FBXu" alt=""><figcaption></figcaption></figure>

### **Step 2: Tag Ontology Concepts**

Go to **Data** → **Ontology** and view where RootCause.ai has already created joins between different **Entity**, **Time**, or **Location** nodes. These are where different datasets are talking about the same thing.

If you see a missing join, or a join that shouldn't be there, you can click on it and make changes. For more advanced operations, like editing or adding individual concepts, see [Ontology Concepts](/user-guide/ontology-concepts.md).

### **Step 3: Create a Data View**

From the Ontology, you can create a combined Data View from multiple datasets for use in causal modeling and simulations. Simply click **+ New View**" on the bottom-right, and then click on one of the joined nodes.

<figure><img src="/files/ZQgXBgTUyAN0rCs8fQer" alt=""><figcaption></figcaption></figure>

In the above example, you would press **+ New View** and then **Customer ID** where a join exists between both datasets.

You're now ready to create a digital twin. If you want to perform operations or transformations on the data beforehand, you can find more details at [Data Views](/user-guide/data-views.md).

### **Step 4: Create a Digital Twin**

Go to **Digital Twin** and select your data view.

<figure><img src="/files/BLCTO4C2F5qTxMk2P8GT" alt=""><figcaption></figcaption></figure>

Choose "Auto Discovery" to let RootCause.ai find causal relationships automatically. This typically takes a few minutes depending on your data size. See [Creating a Digital Twin](/user-guide/creating-digital-twin.md).

<figure><img src="/files/wbmclRuPtU5l35Bcc397" alt=""><figcaption></figcaption></figure>

### **Step 5: Run Simulations**

Once discovery is complete, run simulations to test interventions, find optimal actions, or explain outcomes. This is where insights turn into action. See [Simulations](/user-guide/simulations.md).

<figure><img src="/files/fFcx3IU7RqWeZbEouutr" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.rootcause.ai/start-here/quick-start-tutorial.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.