> For the complete documentation index, see [llms.txt](https://cleyrop.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cleyrop.gitbook.io/docs/documentation-fr-en/getting-started/tutoriel-dintroduction.md).

# Introductory tutorial

This tutorial guides you step by step through discovering Cleyrop's main features.

In a few minutes, you will:

1. Log in to the platform,
2. Load a dataset,
3. Create a transformation,
4. Visualize your data,
5. Use Le Druide,
6. Build a first simple custom assistant (SQL or RAG).

## Login & authentication

### First login <a href="#premiere-connexion" id="premiere-connexion"></a>

You have received a first-login email to configure your account:

* Choose a **password** to securely access your account.

{% hint style="info" %}
The subject is "Welcome to Cleyrop"
{% endhint %}

Next, to log in, you need:

* your Cleyrop instance URL
* username
* password

#### Expired link <a href="#premiere-connexion" id="premiere-connexion"></a>

The link expires after 12 hours; if the link has expired, ask your platform manager to send you a login email again.

### MFA setup

If MFA (*multiple factor authentication)* is enabled for your instance and your account, you must first **configure access from your device** (mobile or computer).

1. Scan the QR code from your device using one of the dedicated apps on your mobile: Google Authenticator, Microsoft Authenticator, Free OTP
2. Name your device
3. Then configure your password

<figure><img src="/files/c421ef914b06bd8cf8fb784803af8e57a10622ca" alt="" width="375"><figcaption></figcaption></figure>

## Tutorial 1 - Load a dataset

**Objective:** Import a data file (CSV, Excel, JSON, etc.) to make it usable on the platform.

**Steps**

1. From the home page of a project or **My Studio**, go to Library, Datasets tab, click + `Add`.
2. Choose Local import
3. Select or drag your file and follow the creation steps.
4. Once the import is complete, the dataset appears in the project's dataset list.
5. Check the preview from the dataset details page to verify consistency.

**Good to know**

* Imported datasets are stored in a secure project area.
* You can define a level of **sensitivity** (Internal, Restricted, Sensitive).

## Tutorial 2 - Create a transformation

**Objective** : Clean, filter, or enrich your data to prepare it for analysis.

**Steps:**

1. Open the Dataflows tab of your project or My Studio.
2. Click Create a Dataflow then add your dataset as input.
3. Choose a transformation:
   * Low code to filter, join, or aggregate columns,
   * Python / PySpark / SQL to write your own scripts.
4. Click Run to launch the transformation.
5. Once the job is finished, view the output dataset.

**Good to know**

* Execution sessions are parallelized on your cluster (Spark or Python).
* You can view execution logs to diagnose any errors.

## Tutorial 3 - Visualize data

{% hint style="warning" %}
Data Visualization is available only to customers who subscribed before May 2026. This feature has been decommissioned for customers from that date onward.
{% endhint %}

**Objective:** Create a **interactive dashboard** to explore your results.

**Steps**

1. Go to the Data Visualization tab of the project or My Studio.
2. Click Create a dashboard.
3. Go to the library, select the output dataset you want to visualize, and press the button **Link to dashboard**
4. Open the dashboard and go to the staging menu to build it
5. Add and configure your chart tiles: line charts, bars, maps, KPIs, etc.
6. Save and share the dashboard with other users.

**Good to know**

* You can add a dashboard to your favorites to access it faster.
* Only authorized users (Viewer, Data Worker, Business Analyst…) can view or modify a dashboard.

## Tutorial 4 – Use Le Druide

**Objective** : Discover how to use Le Druide, Cleyrop's secure conversational AI assistant, to interact with your data and test intelligent tools.

**Steps**

1. Click **New Chat** from the side menu.
2. Add **a PDF attachment** to analyze a document in the conversation.
3. Enter your question (e.g. “Summarize this document in 5 points.”) in the chat field to get an instant answer.
4. Activate a **Tool** in the dedicated panel such as **Internet Search**
5. View the history or start a new session to begin with a blank context.

**Good to know**

* 100% sovereign environment and models.

## Tutorial 5 - Create a custom assistant

**Objective** : Create an AI assistant that interacts with your data.

**Option 1 — SQL Assistant**

1. Go to the AI Assistants tab → Create an assistant.
2. Choose the template **GenInsight (SQL)**.
3. Continue configuration by selecting a dataset accessible from the project.
4. Ask your first questions (“What is the number of rows?”, “Which customers have the most orders?”).
5. The assistant automatically translates your queries into SQL and returns the results.

**Option 2 — RAG Assistant**

1. Go to AI Assistants → Corpus → Create a corpus.
2. Load one or more documents (PDF, DOCX, TXT…) from the project's Work Data (Library > Work Data tab
3. Once vectorized, create an assistant with the Knowledge Manager (RAG) template based on this corpus.
4. Ask your questions: “What does the report say about 2024 performance?”, “What risks have been identified?”

\
**Good to know**

* SQL assistants allow you to query your structured datasets directly.
* RAG assistants leverage text documents through semantic search..