> For the complete documentation index, see [llms.txt](https://docs.expel.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.expel.io/connect-your-technology/a-c-integrations/abnormal-ai-setup-for-workbench.md).
# Abnormal AI Setup for Workbench
The Abnormal AI integration allows Expel to apply our detection strategy to your Abnormal AI alerts and pull them into the Workbench queue for investigation and remediation.
## Prerequisites
1. You must have the [Organization Admin role](/workbench-setup/get-started/add-and-manage-users/user-role-rights.md) in Workbench to set up this integration.
2. You must have admin access in Abnormal AI to create an API token.
## Step 1: Create an Access Token
To integrate the technology with Workbench, you need to create secure credentials to the API.
{% hint style="info" %}
Abnormal AI is requiring customers to migrate **legacy** REST API tokens to a new management system. Existing tokens are marked "Legacy" and continue to work during migration, but they cannot be rotated. For legacy tokens, you can only edit the IP safelist or revoke the token. **All legacy tokens automatically expire on April 30, 2027**. To maintain uninterrupted API access, create a new token using the steps below to replace each legacy token before the expiration date.
{% endhint %}
1. [Log in to Abnormal AI](https://portal.abnormalsecurity.com/) using an account with admin access.
2. Navigate to [**Settings > Integrations**](https://portal.abnormalsecurity.com/home/settings/integrations).
3. Scroll down to the **API Token Management** section and select **Create New Token**.
4. Select **REST API** as the integration type, and select **Next**.
5. Choose a token scope depending on your environment:
* **Tenant (Single Tenant)** - select this to isolate the integration to a single tenant.
* **Customer (All Current and Future Tenants)** - select this if your organization manages multiple tenants under a single Abnormal account.
6. Select **Next**.
7. Select **Custom Access**, and choose the following endpoints:
* Threats - Read Access
* Threats - Read Sensitive Access
* Threats - Write Access
* Messages - Read Sensitive Access
* Employees - Read Sensitive Access
* Vendors - Read Sensitive Access
{% hint style="info" %}
Both **Threats Read Access** and **Threats Read Sensitive Access** are required. Read Access covers alert polling and the health check, Read Sensitive covers attachments and links. Access levels are fixed at creation, so an under-scoped token has to be recreated rather than edited. **Threats Write Access** is needed for Expel email remediation actions.
{% endhint %}
8. Select **Next**.
9. Configure the following:
* **Token Name** - enter an Expel-identifiable name, like "Expel MDR".
* **Description** (optional) - note that this token is for the Expel integration.
* **Token Expiry** - we recommend 365 days, unless your organization's policy requires shorter.
* When a token expires, Alerts will stop being ingested. Rotating a token in the Abnormal portal invalidates the previous value immediately, so the token must be updated on the Workbench device at the same time.
* Abnormal returns a 403 error for an expired token, so Workbench will show "credentials don't have permission to connect" rather than an "expired credential" message.
* To prevent access interruption, you may opt to receive email notifications before your token expires. Configure the API token expiry event type in the [Abnormal Portal Notification Settings](https://abnormalsecurity.my.site.com/support/s/article/Abnormal-Portal-Notifications-Settings).
* **IP Safelist** - add the listed IP addresses from [Configure an IP Allow List](/workbench-setup/configure-an-ip-allow-list.md).
10. Select **Next**.
11. Review your token information, then select **Create Token**.
12. **Copy and save** the token in a safe place for use in a later step. *This token value will only be shown once.*
13. Select **Done**.
## Step 2: Add Abnormal AI as a Security Device in Workbench
Now that you have an access token, you can configure the integration in Workbench.
1. [Log in to Workbench](https://workbench.expel.io/auth/login?orig=%2F).
2. In the side menu, navigate to **Organization Settings > Security Devices**.
3. Select **Add Security Device**.
4. In the search box, type “Abnormal” and then select the **Abnormal AI** integration.
5. A configuration pane displays. Complete the fields as follows:
* **Name** - enter a name that might help you more easily identify this integration, such as “CompanyName Abnormal AI”; this name will display in Workbench under the Name column, and is a text string that you can filter on.
* **Location** - enter the location of your integration, for example “cloud.” This is also a text string that you can filter on, so we recommend being consistent with location naming across your Expel integrations.
* **Abnormal Security API endpoint URL** - enter the base URL for your environment:
* U.S.: `https://api.abnormalplatform.com`
* EU: `https://eu.rest.abnormalsecurity.com`
* FedRAMP: `https://rest.abnormalsecurity.us`
* **Abnormal Security API authentication token** - enter the API token you saved in [Step 1](#step-1-create-an-access-token).
6. Select **Save**.
7. On the console access screen, select **No thanks, I will not provide console access** from the dropdown.
Your device should be created successfully within a few seconds. A few reminders:
* After your connection is healthy, it will take some time for your device to begin polling and receiving data.
* To check on the status, select the downward arrow for your device in the first column and choose **View details**.
* Polling will happen first; data will be received after that. **You must refresh the page to see updates.**
* If your device does not begin polling within 15 minutes, and does not begin receiving data within 30 minutes, [contact our support team for help](/support/how-to-reach-us.md).
* To check if alerts are coming through, navigate to **Dashboards > Alert Analysis**. Scroll to the device you want to check, and select the **Expel Alerts** tab to reveal more alert information. It can take 36 to 72 hours for alerts to appear after setup, as we [tune your device](/workbench-reference/alerts/how-expel-alerts-work.md#device-tuning).
## Step 3: (Optional) Set Up Auto Email Deletion
The first two steps of this guide enable Expel to ingest the Abnormal AI alerts and investigate any malicious activity. This optional configuration lets us use detection strategy to immediately delete any email that Abnormal AI identifies as malicious *as soon as we ingest its associated alert*.
This means those emails will be assumed as correctly flagged by Abnormal AI as malicious, and then deleted for every email user without a SOC investigation. We will instead focus all of our SOC efforts on other types of Abnormal AI alerts. However, the Abnormal AI alert that references the deleted email will still be available to our SOC analysts and can be correlated to other suspicious activity where needed.
[Learn more about how remediation works](/connect-your-technology/about-integrations/about-mdr-for-email.md#h_01jrjp0rrke00fk9dm80bevyg8) in this process.
{% hint style="warning" %}
You must have Microsoft 365 or Google Workspace as your email provider to use this feature.
{% endhint %}
### Step 1: Enable Permissions in Your Email Provider
1. Set up appropriate permissions within your email provider by selecting one of the links below for instructions.\
***If you have already enabled the Remove Malicious Email auto remediation in support of a different integration, you can skip this step (because you will have already set this part up).***
* [Microsoft 365](/workbench-setup/auto-remediations/remove-malicious-email/microsoft-365-remove-malicious-email.md#step-2-add-an-additional-api-permission): Follow *only* the Step 2 section of this guide, then return to this page and continue to step 2.
* [Google Workspace](/workbench-setup/auto-remediations/remove-malicious-email/google-workspace-formerly-g-suite-remove-malicious-email.md#h_01jh5zgcgw8ekzjnfd2tzwjvat): Follow *only* the Step 1 and Step 2 sections of this guide, then return to this page and continue to step 2.
### Step 2: Enable the Auto Remediation in Workbench
1. Contact your Customer Success Manager (CSM) and ask that they enable the **Auto-Remediate Suspicious Delivered Email Alerts** (`org.preference.email.auto_remediate_delivered`) value in Workbench.
---
# 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.expel.io/connect-your-technology/a-c-integrations/abnormal-ai-setup-for-workbench.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.
