> ## Documentation Index
> Fetch the complete documentation index at: https://docs.genie-app.de/llms.txt
> Use this file to discover all available pages before exploring further.

# Workspace guardrails: control what Genie AI will discuss

> Turn on guardrails to block harmful content, off-limits topics, and banned words in Genie AI conversations. Configure everything in plain language — a Teams-plan feature for owners and admins.

Genie AI checks every message sent in workspace chat against your workspace's guardrails before it answers. Workspace owners and admins configure guardrails in plain language — no technical setup — deciding what kinds of content Genie AI should refuse to engage with.

<Note>
  Guardrails are available on the **Teams** plan. Only **owners** and **admins** (or a custom role granted the right permission) can configure them. All workspace members are subject to guardrails once they're turned on.
</Note>

## Open Guardrails settings

Click the account row at the bottom of the workspace sidebar, choose **Workspace settings**, then open **Guardrails**.

## Turn guardrails on

Toggle **Guardrail protection** on. If nothing has been configured yet, Genie starts from a set of protective defaults that you can adjust from there. At least one protection must stay active at all times — an empty guardrail configuration can't be saved.

## What you can configure

### Harmful content

Set a strength for each category — **Off**, **Relaxed**, **Balanced**, or **Strict**:

| Category              | What it catches                                                                                         |
| --------------------- | ------------------------------------------------------------------------------------------------------- |
| Hate speech           | Discrimination or attacks on people because of who they are                                             |
| Insults               | Demeaning, humiliating, or bullying language                                                            |
| Sexual content        | Explicit or suggestive sexual content                                                                   |
| Violence              | Glorifying or threatening physical harm                                                                 |
| Illegal activities    | Help with crimes, fraud, or other wrongdoing                                                            |
| Manipulation attempts | Attempts to trick Genie AI into ignoring its rules ("jailbreaks") — only applies to what a person sends |

### Off-limits topics

Add named topics that Genie AI should refuse to discuss in your workspace — for example, "Investment advice." Each topic gets a plain-language description of what counts as that topic, plus optional example messages to help Genie recognize it.

### Blocked words

Turn on a built-in profanity filter, and add your own list of banned words or phrases specific to your organization — one per line.

### Message shown when blocked

Optionally write your own message, shown to a member instead of Genie's answer when a guardrail blocks their message. Leave it blank to use Genie's default explanation.

## Blocked messages log

The Guardrails page keeps a log of recent interventions: which category or topic triggered the block, where it happened (workspace chat or a project), who sent it, and when. The message content itself is never stored — only the reason it was blocked.

## Manage guardrails from workspace chat

Ask the Genie workspace AI in plain language:

* *"Turn on guardrails and block sexual content and violence at the strictest level"*
* *"Add an off-limits topic for legal advice"*
* *"Show me recent blocked messages"*
* *"Turn off the manipulation-attempt filter"*

Genie AI asks you to confirm before weakening or disabling a protection.

<Tip>
  Open the **Guardrails** page and click **Ask Genie AI** for a ready-made prompt that walks you through setting up guardrails for your team.
</Tip>

## Related pages

<CardGroup cols={2}>
  <Card title="PII rules" icon="shield" href="/workspaces/pii-rules">
    Detect and block sensitive data like credit card numbers and API keys in chat.
  </Card>

  <Card title="Governance" icon="check-check" href="/workspaces/governance">
    Review projects and enforce compliance rules across your workspace.
  </Card>

  <Card title="Genie MCP Server" icon="code" href="/workspaces/mcp-api">
    Manage guardrails programmatically from any MCP client.
  </Card>

  <Card title="Members and roles" icon="users" href="/workspaces/members">
    Grant the guardrails permission to a custom role.
  </Card>
</CardGroup>