# Connections

Before an AI agent can be used, a connection to an AI provider must be configured.\
Connections are managed centrally and can be reused by multiple agents.

<figure><img src="/files/8HVSYDgKqmitwUdb1uNr" alt=""><figcaption></figcaption></figure>

#### Steps

* Navigate to **Data Studio → Connections**
* Click **Add Connection**
* Configure the connection as follows:

#### General settings

| Field     | Description                                                                                                                      |
| --------- | -------------------------------------------------------------------------------------------------------------------------------- |
| **Name**  | A descriptive name for the connection (e.g. `openai-api-key`).                                                                   |
| **Level** | Determines the scope of the connection. Use **Collection** to make the connection available to all agents within the collection. |
| **Type**  | Select **API headers**.                                                                                                          |

#### Setting secret values

After creating the connection, the actual secret values (such as API keys) must be set separately.

This separation ensures that sensitive information is stored securely and is not visible in the connection definitions.

**Steps**

1. Navigate to **Data Studio → Connections**
2. Locate the created connection
3. Click the **three-dot menu** next to the connection
4. Select **Set values**

A dialog will open showing the configured headers, where the secret values can be entered.


---

# 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://academy.any2info.com/any2info-academy/no-code-platform/ai-studio/connections.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.