> For the complete documentation index, see [llms.txt](https://captic-2.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://captic-2.gitbook.io/docs/overview/good-to-know/data-lifecycle.md).

# Data Lifecycle

What data do we collect, where does it go, and why? We’re here to make that crystal clear, so you can rest easy.

## What data we collect and why

For a detailed explanation of why we collect data, check out the [**ML Lifecycle**](/docs/overview/good-to-know/ml-lifecycle.md) section. In short, a typical Captic system continuously collects several types of data to ensure everything runs smoothly and your AI models keep improving.

### Types of Data We Collect:

1. **Device Metrics** 
   * **Why**: To monitor hardware performance and detect potential issues early.
2. **AI Logs**
   * **Why**: To track AI model performance over time and identify any anomalies.
3. **Images**
   * **Why**: To retrain models, enhance accuracy, and continuously improve system performance.

The amount of data collected depends heavily on the application. Some use cases need more data than others.

### Why Data Matters for AI

AI models are **taught, not programmed**. To excel at a task, they need:

* **Many examples** to learn from.
* The ability to identify patterns and signals that outperform traditional systems.

The more data we collect, the better your AI models can perform. But don’t worry — **data security is our top priority**.

{% hint style="info" %}
More details can be found in the [ML Lifecycle](/docs/overview/good-to-know/ml-lifecycle.md) section.
{% endhint %}

{% hint style="info" %}
For more details on how we protect your data, check out the [Security](/docs/overview/good-to-know/security/security.md) section.
{% endhint %}

## Where is your data stored and how

### Data Flow in a Nutshell

1. Data is collected by your **Captic systems** on-site in your manufacturing environment.
2. This data is **continuously or periodically uploaded** to a dedicated **Azure Resource Group** we’ve provisioned for your company.

### Where Your Data Lives

In your Azure Resource Group, data is securely stored in:

* **Azure Blob Storage**\
  For storing images and other large data files.
* **Azure Log Analytics**\
  For tracking logs, metrics, and insights.

<figure><img src="https://482575286-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F22HCD2cZG8ud6cPRBzVQ%2Fuploads%2Fq0nSTNj4rYJUw8qdkXfV%2Fimage.png?alt=media&amp;token=996515e4-feb5-48ee-a227-59165e4bb252" alt=""><figcaption></figcaption></figure>

### Who Has Access

By default, only **Captic personnel** who work directly on your systems have access. We strictly follow the **least-privilege principle**.

Need your internal IT team to access the data? No problem! We’re happy to grant access using your company’s **Microsoft accounts**. This way, your team can build custom tools and dashboards on top of the data.

{% hint style="info" %}
We don’t mess around when it comes to securing your data. For a deep dive into our security practices, check out the **Security** section.
{% endhint %}

{% hint style="info" %}
If you have any questions or need more details, drop us a line at <security@captic.com>.
{% endhint %}