# Automated Actions

After a document review is completed, Protege AI can perform various automated actions to streamline your workflow based on user-defined risk thresholds.

## Overview

Automated actions eliminate manual steps by automatically responding to review results. Actions are triggered when policy feedback meets specific risk criteria that you define.

For example, if a review identifies fewer policy violations than your threshold, the document can be automatically approved without manual intervention. Conversely, if high-risk issues are detected, detailed comments can be automatically posted to your task management system.

## Available Actions

### Auto-Approval

If the identified risks are below your user-defined auto-approval threshold, documents can be automatically approved, eliminating the need for manual review.

**Benefits:**

* Speeds up review cycles for low-risk content
* Reduces reviewer workload on routine changes
* Maintains consistency in approval criteria
* Ideal for minor updates to previously approved content

**Use Cases:**

* Small changes to marketing assets
* Updates to previously reviewed materials
* Content with minimal or no policy violations
* Routine template-based documents

### Auto-Comment Generation

The AI can automatically generate and add comments to your task management system for issues identified during the review.

**Features:**

* Detailed insights about each policy violation
* Suggested actions for remediation
* Risk level indicators (High, Medium, Low)
* Links back to specific feedback in Protege

When identified risks exceed your threshold, all problems are consolidated and posted as a comment in the requester's ticket, ensuring that high-risk issues are promptly flagged and addressed.

## Configuration

### Setting Up Automated Actions

1. Navigate to the **Task Manager** where you want to enable automated actions
2. If there is no Default Evaluation Type set, select one to run on the Task Manager
3. Toggle on **Autocomment** and/or **Autoapprove** based on your workflow needs
4. Click the ⚙️ icon to configure individual policy thresholds for each action
5. Define risk levels and occurrence counts for each policy type
6. Press ✔️ to save your settings

### Configuring Thresholds

For each policy in your evaluation:

* Set the **risk level** threshold (High, Medium, Low)
* Define the **occurrence count** that triggers the action
* Different thresholds can be set for auto-approval vs. auto-commenting

**Example Configuration:**

* Auto-approve if: 0 High risk, ≤2 Medium risk, any Low risk
* Auto-comment if: ≥1 High risk, ≥5 Medium risk

## Action History

View a complete history of all automated actions:

1. Go to **Settings** → **Action History**
2. Review past auto-approvals and auto-comments
3. Filter by date, project, or action type
4. Audit automated decisions for compliance purposes

## Best Practices

* **Start Conservative**: Begin with strict thresholds and gradually relax them as you gain confidence
* **Regular Review**: Periodically review action history to ensure thresholds remain appropriate
* **Policy-Specific Settings**: Configure different thresholds for different policy types based on risk
* **Team Alignment**: Ensure your team understands which documents will be auto-approved
* **Audit Trail**: Maintain records of threshold changes for compliance purposes

## Integration with Task Managers

Automated actions work seamlessly with:

* Asana
* Jira
* Smartsheets
* Wrike

Comments and approvals are posted directly to tickets in your connected task management system, maintaining a complete audit trail.

## Disabling Actions

To temporarily or permanently disable automated actions:

1. Return to your Task Manager settings
2. Toggle off **Autocomment** or **Autoapprove**
3. Save your changes

Previous action history is preserved even when actions are disabled.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://gitbook.tryprotege.com/review/review-tool-concepts/document-review/automated-actions.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.