---
title: Using Pylon
description: "How the Langfuse team handles support requests in Pylon: intake, assignment, tagging, and the conventions we follow on every ticket."
---

# Using Pylon

This guide outlines our process for handling support requests at Langfuse. For this, we use [Pylon](https://app.usepylon.com/) ([docs](https://docs.usepylon.com)):

- Centralize our [support channels](/support) in a single inbox
- Manage escalation levels and track SLAs
- Link customer requests and reported bugs to Linear issues

Everyone gets access to Pylon during onboarding.

## What is the Process in Pylon?

1. **Unified inbox**: Pylon is synced with our [support channels](/support): **Slack** Connect channels, **MS Teams** channels, **email** support addresses, **GitHub Discussions** (Support and Ideas), and **in-app support form**. Pylon uses AI to merge messages into support tickets in case a user uses multiple messages for a single request.
2. **1st level support**: Screens the inbox regularly, answers questions
   - Assign 2nd level [owner](/handbook/how-we-work/ownership) if escalation is needed
   - Generally, escalate bug reports and feature requests to owner. Owner takes care of linking to their Linear backlog (see [product ops](/handbook/product-engineering/how-we-work/product-ops)).
3. **Owner (engineer, GTM)**: fixes/logs the issue, notes feedback, and gives technical advice.
4. **Close the loop**: Resolve immediately or log an issue and ping the user once fixed + update docs

## How to use Pylon?

### Core application screen

  ![Pylon Screenshot](/images/handbook/using-pylon/pylon-screenshot.png)

1. Status of an Issue.
2. Assignee of an Issue. You own the issue if you are assigned.
3. Customer Tier: Check if they are paying us.
4. Leave internal notes and tag people.
5. Use Pylon to directly reply in Slack/MS Teams/email/chat widget.

### Personal workflow

- If you are not on first-level support duty:
  - You can focus on the view `My issues (only assigned)`.
  - It is expected that you clear these out at least once a day.

### Recommended Notification Settings

- Subscribe to all events related to threads assigned to you
- In general, we use Slack async. For most members of the team, we recommend enabling Pylon notifications in Slack as the default in order to move fast on customer communication.
- If you are on PTO, please turn on `Away Mode` in order to (1) unassign threads upon new responses from you and (2) disable any automation that auto-assigns tickets to you

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/handbook/support/using-pylon.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.