---
title: "Comprehensive Guide to Multimodal AI Assessment Configuration"
slug: "configuring-ai-assessment"
description: "Discover how to configure and utilise the Multimodal AI Assessment rule to enhance your system's analysis capabilities. Learn step-by-step setup today."
updated: 2026-03-17T12:11:07Z
published: 2026-04-27T10:00:00Z
canonical: "documentation.encodify.com/configuring-ai-assessment"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://documentation.encodify.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Configuring Multimodal AI Assessment

## Guide to Configuring and Using the Multimodal AI Assessment Rule

This guide provides a comprehensive overview of how to configure and use the Multimodal AI Assessment rule. This functionality allows the system to send text data and media files from specific modules to an AI service and record the resulting analysis back into the system.

### 1. Rule Configuration

The configuration is divided into five primary configuration steps.

#### Step 1: Basic Info & Conditions

This section defines the rule's identity and the specific trigger criteria.

| Field | Description |
| --- | --- |
| **Name** | Enter a unique name for the rule (e.g., "Product Compliance Review"). |
| **Description** | (Optional) Briefly explain the purpose of this AI assessment. |
| **Active Toggle** | Ensure this is switched On for the rule to run. |
| **Type** | Select Multimodal AI Assessment from the dropdown. |
| **Sort Order** | Determines the priority if multiple rules are triggered simultaneously. |
| **Module** | Select the primary module (e.g., Products) that will trigger the assessment. |
| **IF Condition** | Set the criteria that must be met for the rule to be executed. |

![Form for creating a new automation rule with conditions and settings.](https://cdn.document360.io/3a63e0a8-1221-4570-aaa1-d43f9b95a612/Images/Documentation/1.png)

Form for creating a new automation rule with conditions and settings.

#### Step 2: Actions (Main Item Fields)

Identify which specific field data from the main item should be sent to the AI.

- **Analyzed Module:** This defaults to the module selected in the **Conditions** section.
- **Analyze Data in Fields:** Click **Add Field** to specify the field data you want the AI to evaluate. It is also possible to select **File** fields and define if original file or its rendition should be sent for evaluation.

![Form fields for analyzing product descriptions and campaign text in an AI module.](https://cdn.document360.io/3a63e0a8-1221-4570-aaa1-d43f9b95a612/Images/Documentation/Screenshot 2026-03-17 at 11.18.48.png)

Form fields for analyzing.

#### Step 3: Linked Modules Fields

You can enrich the AI request with linked item data and files.

- **Linked Module:** Select the linked module. Note, that only modules with module links to the main module can be selected. Direct links from main module to linked modules are not supported.
- **Link Field:** Identify the field that connects the two modules.
- **Filter by Field/Values:** (Optional) Narrow down which linked items are sent (e.g., only items where Status is "Available" or "Ready").
- **Analyze Data in Fields:** Select the field(s) to send.
- **Media Holder:** For file fields, specify if original file or rendition is sent for assessment.

![Fields in Linked Modules for linking content library and analyzing media files.](https://cdn.document360.io/3a63e0a8-1221-4570-aaa1-d43f9b95a612/Images/Documentation/Screenshot 2026-03-17 at 11.20.27.png)

Adding fields from the Linked Module(s)

#### Step 4: AI Prompt

This is the instruction sent to the AI.

- **Prompt for AI:** Use the rich text editor to provide clear, concise instructions. Prompt field supports markdown.

**Example:** "Analyze the provided product description and the attached media files. Check for brand consistency and safety compliance. Return a risk score and a brief summary."

![](https://cdn.document360.io/3a63e0a8-1221-4570-aaa1-d43f9b95a612/Images/Documentation/Screenshot 2026-03-17 at 11.24.43.png)

Instruction text input area for AI prompt creation in a document editor.

#### Step 5: Save the Result

Define how the AI's response should be stored.

- **Status Field Mapping:** Map the statuses to your main module's field options so you can track progress (e.g., Map "*In Progress*," "*Completed,*" and "*Failed*").
- **Storage Method:** Choose between **Save in Current Item** or **Create Inline Item**.

AI’s output field mapping is the same regardless which save method is selected. Saving to separate module will require module and linked field specified.

- **Confidence Score:** Usually a numeric (decimal) or text field.
- **Assessment:** Text or Text box field to store assessment result.
- **Status Code & Error Message:** Vital for troubleshooting failed calls.

![Form fields for status updates and assessment results in a user interface.](https://cdn.document360.io/3a63e0a8-1221-4570-aaa1-d43f9b95a612/Images/Documentation/Screenshot 2026-03-17 at 11.48.44.png)

Form fields for status updates and assessment results.

### 2. Rule Execution (Triggering)

This rule does not have a subtype or event that triggers it. Instead, it is governed by the following logic:

- **Action Trigger:** Execution is triggered by a Create or Update action on main item within the selected main module.
- **Status Gatekeeper:** The rule will only run if the mapped **Status** field value does not equal the options mapped as "In Progress," "Failed," or "Completed." This prevents infinite loops.
- **Filter Match:** The item must meet the specific criteria defined in the Conditions section (if any).

Once triggered, the item status will shift to "In Progress" until the AI service returns the data to the mapped result fields. Successful assessments will set main item’s status to the option mapped as “Completed Successfully“.

![Information about GreenProtect silverfish trap, including product details and campaign offer.](https://cdn.document360.io/3a63e0a8-1221-4570-aaa1-d43f9b95a612/Images/Documentation/Screenshot 2026-03-17 at 12.58.43.png)

Example of the main item with the linked assessment result and successfully completed status.

### 3. Recommendations and Limitations

#### General AI Caution

AI can make mistakes. It is recommended to add Help Text to the result fields (e.g., "This field is populated by AI; please verify for accuracy").

#### Technical Limitations & Risks

- **Consistency:** The same payload may return slightly different results across multiple calls.
- **Contradictions:** Occasionally, the numerical score and the text assessment may contradict.
- **Data Volume:** Large volumes of data (e.g., a single file >100MB or more than 30 separate files) can significantly degrade the quality of the AI's output.
- **Race Conditions**: If the "Copy referenced items" feature is enabled for the main module, the AI rule might trigger before all linked items have finished being created as a result of copy of the main item.
- **Stuck Status**: If an item remains "In Progress" for an extended period, check the webapp logs. If the system fails to update the item with the final response, it may stay in that status until manually reset.
- **File Integrity:**
  - Files with special characters (%0D, %0A) in the name that cannot be downloaded via UI cannot be analyzed.
  - Encrypted or password-protected PDFs will cause an evaluation failure.
  - Files with incorrect or double extensions (e.g., .pdf.exe) may fail.