> For the complete documentation index, see [llms.txt](https://ai-security-docs.akto.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-security-docs.akto.io/agentic-guardrails/how-to/create-guardrail-policies/policy-details-and-scope.md).

# Policy Details and Scope

Define the identity, messaging, and deployment scope of a guardrail policy. These are the sections that decide what a policy is called, what users see when it blocks, and where it applies.

This page covers part of the [Create Guardrail Policies](https://ai-security-docs.akto.io/agentic-guardrails/how-to/create-guardrail-policies.md) form.

## Provide Guardrail Policy Details (Mandatory)

This section defines identifying metadata and user-facing enforcement messages.

{% stepper %}
{% step %}
**Name the policy**

Enter a **policy name** and **description**.
{% endstep %}

{% step %}
**Set the severity**

Select the **severity level** to classify the importance of violations generated by the guardrail policy.
{% endstep %}

{% step %}
**Define the blocked message**

Define the **blocked message** shown when a request is denied.
{% endstep %}

{% step %}
**Reuse the message for responses (optional)**

Enable the option to **apply the same blocked message to responses**, if consistent messaging is required across requests and responses.
{% endstep %}
{% endstepper %}

{% hint style="info" %}
This section is required to create a guardrail policy.
{% endhint %}

<div data-with-frame="true"><figure><img src="https://1895868029-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkpBG2Nfd5ZbNmahr8W6H%2Fuploads%2Fgit-blob-8c3d22edb6ecf17bfa1894c6b3a7006b0bd8d094%2Fimage%20(3)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1)%20(1).png?alt=media" alt="" width="563"><figcaption></figcaption></figure></div>

## Scope

Configure which servers the guardrail should be applied to and specify whether it applies to requests, responses, or both. The coverage controls differ by product.

**Akto Atlas: Agentic Assets**

Choose which assets the guardrail is deployed across:

* **Apply to all** (Recommended): Applies the guardrail to all assets. The panel shows the current counts, for example `46 Agents`, `95 MCP Servers`, and `22 LLMs`, as links you can select to view the full list.
* **Select Agentic Assets**: Target specific assets using a condition builder.

To build a condition:

{% stepper %}
{% step %}
**Choose an asset type**

Under **Where my**, choose an asset type such as **Agents**, **MCP Servers**, or **LLMs**.
{% endstep %}

{% step %}
**Select the values**

Use the **are** field to search and select the matching values.
{% endstep %}

{% step %}
**Layer or reset conditions**

Select **Add condition** to layer additional conditions, or **Clear all** to reset the configuration.
{% endstep %}
{% endstepper %}

**Include or exclude specific assets**

In both Akto Atlas and Akto Argus, each condition can either **include** or **exclude** its matches, so you can apply a policy broadly and carve out exceptions.

* Include or exclude specific **agents**, **MCP servers**, **LLMs**, **devices**, and **users**.
* Combine include and exclude conditions in the same policy, for example apply to all agents except a trusted internal agent.

{% hint style="info" %}
See how many MCP servers and agent servers a policy touches before you deploy it. **Apply to All** now shows the full scope up front.
{% endhint %}

**Akto Atlas: Device Tags & Users**

Choose which users and devices the guardrail applies to:

* **Apply to all** (Recommended): Applies the guardrail to all users in your organisation, for example `136 Users`.
* **Select Device Tags & Users**: Choose specific device tags or users using the same condition builder.

To build a condition:

{% stepper %}
{% step %}
**Choose an attribute**

Under **Where my**, choose an attribute such as **Groups**, a specific **user**, or a specific **device**.
{% endstep %}

{% step %}
**Select the values**

Use the **are** field to search and select the matching values. To target users by **email address**, select the user's email as the value.
{% endstep %}

{% step %}
**Layer or reset conditions**

Select **Add condition** to layer additional conditions, or **Clear all** to reset the configuration.
{% endstep %}
{% endstepper %}

The number of matching users updates as you build the condition, for example `Applies to 1 user with the current selection.`

<div data-with-frame="true"><figure><img src="https://1895868029-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkpBG2Nfd5ZbNmahr8W6H%2Fuploads%2Fgit-blob-64dc9f57f886827382842ad4a962cfe35f447eb5%2Fimage%20(221).png?alt=media" alt="" width="563"><figcaption></figcaption></figure></div>

**Akto Argus: Coverage**

Akto Argus shows a single **Coverage** section instead of separate Agentic Assets and Device Tags & Users sections:

* **Apply to all** (Recommended): Applies the guardrail to all discovered assets. The panel shows the current counts, for example `60 Agents & 31 MCP Servers`, as links you can select to view the full list.
* **Advance Configuration**: Build a condition to target specific assets.

To build a condition:

{% stepper %}
{% step %}
**Choose an asset type**

Under **Where my**, choose an asset type such as **AI Agents** or **MCP Servers**.
{% endstep %}

{% step %}
**Select the values**

Use the **are** field to search and select the matching values.
{% endstep %}

{% step %}
**Layer or reset conditions**

Select **Add condition** to layer additional conditions, or **Clear all** to reset the configuration.
{% endstep %}
{% endstepper %}

<div data-with-frame="true"><figure><img src="https://1895868029-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FkpBG2Nfd5ZbNmahr8W6H%2Fuploads%2Fgit-blob-8c5f6468eedc0978ecd3afcbc44befe7e984fba8%2Fimage%20(222).png?alt=media" alt="" width="563"><figcaption></figcaption></figure></div>

{% hint style="info" %}
Some agentic assets may show as disabled in **Advance Configuration**. **Block** rule behaviour requires the target server to run in inline (sync) mode.
{% endhint %}

**Akto Atlas: Work & Personal Accounts (Beta)**

Apply the policy based on the account used to sign in to AI tools:

* **All accounts** (Recommended): Applies to both work and personal accounts.
* **Personal accounts only**: Applies to personal accounts only. Work accounts are excluded.

Use **Personal accounts only** to enforce stricter guardrails on usage outside your organisation-managed identities without affecting work accounts.

**Rule Behaviour**

Choose how Akto responds when a guardrail condition is triggered:

* **Block**: Stops the request or response when the condition is met.
* **Alert**: Generates an alert for review without blocking content.
* **Human Approval**: Blocks the triggering attempt and routes it to your designated approvers through the **Needs Approval** tab in Guardrail Activity, where they approve or deny it. See [Manage Human Approval Requests](https://ai-security-docs.akto.io/agentic-guardrails/how-to/manage-human-approval-requests.md) for the full workflow.

**Application Settings**

Specify whether the guardrail should be applied to responses and/or requests:

* **Apply guardrail to requests**: Evaluates user inputs before processing.
* **Apply guardrail to responses**: Evaluates model outputs before delivery.

You can enable either option independently or both together based on enforcement requirements.

{% hint style="info" %}
**Browser LLM Enforcement**

For Browser LLMs (**chatgpt.com**, **gemini.google.com**, **claude.ai**, **copilot.microsoft.com**, and **grok.com**), Akto enforces guardrails on the request path in real time, stopping risky prompts before they ever reach the model. Response-side enforcement for these domains is coming soon.
{% endhint %}

{% hint style="warning" %}
**Guardrail Deployment Scope Behaviour**

By default, a newly created guardrail policy applies to **all** agentic assets: all **Agents**, **MCP Servers**, and **LLMs**.\
To restrict enforcement, select **Select Agentic Assets** in the **Scope** section and choose the specific assets to target.
{% endhint %}

{% hint style="info" %}
**OWASP Agentic Risk Tags**

Guardrail policies include OWASP-aligned risk tags. You can click each tag in the UI to understand the associated risk category and its security impact on agent behaviour.
{% endhint %}
