> 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/bindplane-agent.md).
# Bindplane Agent
Build, edit, and understand your telemetry pipelines by chatting in plain language, right inside Bindplane.
{% hint style="info" %}
Bindplane Agent is in private beta. To request access, please fill out this [form here](https://forms.gle/hpJ5d4AAvodwFkGE8).
{% endhint %}
Bindplane Agent is your AI assistant inside Bindplane, ready to act on what you describe in plain language. Bindplane Agent will build and refine your telemetry pipelines, answer your questions, and make changes for you, right where you are working.
### Opening Bindplane Agent
Open Bindplane Agent with the button in the corner of the screen, or press `t` from anywhere. Move it, resize it, and dock it to the side of the screen, or keep it floating.
### Building and editing your pipelines
Just describe what you want, and Bindplane Agent makes it happen in the configuration you are viewing. Add or remove sources, destinations, and processors, connect them together, fine-tune their settings, and save reusable pieces to your library. Ask for one change or several at once, and watch each one appear in the graph as the Agent works, whether you are refining an existing pipeline or starting a new one from scratch.
A few things you can ask:
* *"Collect my Windows security logs and send them to Google SecOps."*
* *"Add a source that collects logs from a file."*
* *"Set the batch size on my batch processor to 200."*
* *"Send my Kubernetes logs to Dynatrace."*
### Understanding your pipelines and data
Bindplane Agent can explain what you are looking at, without changing a thing. Ask how telemetry moves through your pipeline, or open a processor node and ask what is in your data and what a processor changed.
A few things you can ask:
* *"Which sources send logs, and where do they go?"*
* *"What fields are in these logs, and what did this processor change?"*
* *"Walk me through what this processor bundle is doing."*
### Chat History
Bindplane Agent 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. You can delete a chat at any time to remove the chat and all of its messages. Saved chats are deleted automatically after 14 days. When your project has a data encryption key configured, chat titles and messages are encrypted at rest using the same encryption technique used for your other Bindplane secrets.
### How your data is used
When AI features are enabled, only the input needed to generate a response is sent for processing. For Bindplane Agent, this includes your configuration, telemetry samples from the node you are viewing, and the messages in your conversation. Your inputs and outputs are never used to train or fine-tune AI models.
Sensitive configuration values such as credentials and API keys are masked with a (sensitive) placeholder before anything is sent, so they are never included in plain text.
Bindplane Agent is off by default. Nothing changes in your environment until an org admin explicitly enables it. For full details, please review the [Data privacy and security](/feature-guides/pipeline-intelligence/data-privacy-and-security.md) page, our [Privacy Policy](https://bindplane.com/legal/privacy-policy), and our [EULA](https://bindplane.com/legal/eula).
### Best practices
Always review the changes Bindplane Agent makes before you apply them to production. The Agent is designed to create correct configurations, but it can make mistakes, so check its work before rolling out configuration changes.
Things to verify:
* Field paths match your actual data structure
* Conditions and filters work as expected
* Processor order is correct for your use case
* Routes send the right telemetry to the right destinations
Start with simple requests and add complexity gradually. Ask the Agent to explain the telemetry at a node to confirm a processor did what you expected before you save and rollout.
---
# 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/bindplane-agent.md?ask=&goal=
```
`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.
