> For the complete documentation index, see [llms.txt](https://docs.bindplane.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bindplane.com/feature-guides/pipeline-intelligence/data-privacy-and-security.md).

# Data Privacy and Security

Understand how Pipeline Intelligence handles your data.

## Opt-in

Pipeline Intelligence AI features are off by default. Nothing is sent for processing until an organization admin explicitly enables them.

## What is sent for processing

When AI features are enabled, only the minimal input data needed to generate a response is sent for processing. This may include:

* Your configuration and resources
* Telemetry samples
* Agent information
* Content snippets

Your inputs and outputs are never used to train or fine-tune AI models.

## Sensitive value masking

Sensitive configuration and resource values, such as credentials and API keys, are masked with a `(sensitive)` placeholder before anything is sent to the model.

## Automatic PII redaction

{% hint style="warning" %}
Although we redact Personally Identifiable Information (PII), we still recommend exercising caution when including personal or confidential information in your prompts.
{% endhint %}

Before any telemetry is sent to the AI model, Pipeline Intelligence detects and redacts common categories of PII, replacing each match with a `[REDACTED]` placeholder. Detection uses the same patterns as the [Redact Sensitive Data](/integrations/processors/redact-sensitive-data.md) processor.

The following categories are redacted:

* Email addresses
* IPv4 addresses
* IPv6 addresses
* MAC addresses
* International Bank Account Numbers (IBAN)
* Credit card numbers
* Social Security Numbers (SSN)
* US phone numbers
* International phone numbers

## Data retention

Data sent to the AI model is used during transmission to generate a response and is not retained. Two features keep data for a limited time:

* [Bindplane Agent (beta)](/feature-guides/pipeline-intelligence/bindplane-agent.md) saves your chat history so you can return to past conversations. Chats are stored per user, per project, and are visible only to the user who created them. Saved chats are deleted automatically after 14 days. When your project has a data encryption key configured, Bindplane Agent chat titles and messages are encrypted using the same encryption technique used for your other Bindplane secrets.
* Global Pipeline Intelligence collects small data snapshots from across your pipelines in order to generate recommendations. Snapshots are deleted as soon as they are no longer needed, and no later than 10 days.

## Third-party AI providers

Pipeline Intelligence sends requests to third-party AI providers to generate responses. The provider used for each feature is listed in the [AI Features table](/feature-guides/pipeline-intelligence/pipeline-intelligence.md#ai-features) on the Overview page. For details on a provider's data handling practices, refer to its privacy documentation. For more information on how Bindplane handles your data, see our [Privacy Policy](https://bindplane.com/legal/privacy-policy), and our [EULA](https://bindplane.com/legal/eula).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.bindplane.com/feature-guides/pipeline-intelligence/data-privacy-and-security.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.