---
title: Which roles can edit prompts and change prompt labels?
seoTitle: "Prompt Permissions and Protected Labels by Role"
description: Members and above can create prompts and move labels. Only Owners and Admins can change protected labels such as production.
tags: [prompt-management, administration]
---

# Which roles can edit prompts and change prompt labels?

| Action                                                                                                                                                                                                     | Minimum project role                             |
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------ |
| View prompts                                                                                                                                                                                               | `Viewer`                                         |
| Create, edit, and delete prompts; add or move labels that are not protected                                                                                                                                | `Member` (`prompts:CUD`)                         |
| Add or remove a [protected label](/docs/prompt-management/features/prompt-version-control#protected-prompt-labels) on a version, delete a prompt that carries one, and manage the list of protected labels | `Admin` or `Owner` (`promptProtectedLabels:CUD`) |

Manage protected labels in **Project Settings → Protected Labels**. The `latest` label cannot be protected. Protected labels are available on the Teams add-on and Enterprise plans on Langfuse Cloud, and on Enterprise self-hosted.

  Protected labels restrict users in the UI. Project API keys with write access to prompts can still move a protected label, for example from a CI pipeline. Treat those secret keys accordingly.

For all roles and scopes, see [Role-based access control](/docs/administration/rbac).

<!-- 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/faq/all/who-can-edit-prompts-and-labels.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>.