> For the complete documentation index, see [llms.txt](https://docs.usepylon.com/pylon-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.usepylon.com/pylon-docs/product-intelligence/feature-requests.md).
# Feature Requests
Automatically extract and organize customer feedback into feature requests to share with your product team.
{% hint style="info" %}
Use AI-synthesized insights and supporting customer evidence to explain feature requests to your product team.
{% endhint %}
### Overview
Pylon's AI extracts product feedback from eligible issues and call recordings, then links it to existing feature requests. It can also create new requests for feedback that doesn't match a request you already track, depending on your settings.
Selecting a feature request displays a detailed description along with information about its origin and evidence from each time it was mentioned.
{% hint style="info" %}
To re-fetch evidence on a Feature Request, use the ellipsis menu to "View prompt". You can update the custom prompt and Regenerate the request.
{% endhint %}
### How it works
* Pylon detects product feedback in eligible issues and call recordings and groups it into feature requests, subject to the settings below.
* Each request displays linked accounts, evidence, and any connected Product Tickets. Click on a piece of evidence to see the original conversation with the customer.
* When a Feature Request is complete, notify your customers by creating [Broadcasts](/pylon-docs/broadcasts/overview.md) from the Feature Request.
* Create a new feature request and Pylon's AI gathers relevant evidence from the customer interactions it processes.
### Automatic creation and call coverage
Go to **Settings > Feature request data > Settings** to control how AI handles new feedback. Changing these settings requires permission to edit Feature Requests.
* **Create feature requests with AI**: allow AI to open a new request when feedback doesn't match an existing request. When this is off, AI still links feedback as evidence on existing requests.
* **Include calls without an account**: include new call recordings that aren't linked to an account, such as prospect calls. Turning this on doesn't reprocess existing recordings.
Call recordings imported as a historical backfill aren't automatically scanned for new feature-request evidence.
### Custom Fields
Feature requests support custom fields to capture structured data beyond the title and description. Add fields for priority, effort, customer segment, or any attribute relevant to your product planning workflow. Custom fields make it easy to filter, sort, and prioritize feature requests based on criteria your team defines.
### Activity Log
The feature request activity log tracks changes made to feature requests over time, including status updates, title and description edits, merges, splits, evidence regeneration, and any actions taken by Pylon AI.
You can view the activity log from the feature request detail sidebar by clicking the ellipsis menu and selecting Activity log, or by pressing the `L` keyboard shortcut.
### Customer Portal
Share feature requests with customers through the [customer portal](https://docs.usepylon.com/pylon-docs/customer-portal/overview). When enabled, customers see the feature requests that are visible to their account, grouped by status.
Feature request visibility in the portal is configured per-account, so you can choose which customers to share information with. Ensure that customers have Portal access with the "Feature Request Read" permission included:
Admin configuration lives under the Customer Portal setting. You can configure custom-field values and custom status labels to share as well.
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.usepylon.com/pylon-docs/product-intelligence/feature-requests.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
