> ## Documentation Index
> Fetch the complete documentation index at: https://koreai-agent-management-platform-dev.mintlify.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Creating Audit Allocations

Creating an allocation follows a three-step workflow: **Settings**, **Allocation Type**, and **Assignment**. Each step builds on the previous one and guides you from initial setup to final auditor assignment.

Navigate to **Quality AI** > **ANALYZE** > **My Allocations**.

<img src="https://mintcdn.com/koreai-agent-management-platform-dev/yl6Z4d0r1rua8MEU/ai-for-service/quality-ai/analyze/allocations/images/create-allocations.png?fit=max&auto=format&n=yl6Z4d0r1rua8MEU&q=85&s=cd1ed7a6af0b8e32b894ee2980f03f6f" alt="Create Allocations" width="532" height="629" data-path="ai-for-service/quality-ai/analyze/allocations/images/create-allocations.png" />

***

## Step 1: Settings

Define the evaluation scope, select the form, and filter the interactions to evaluate.

### Basic Information

| Field               | Description                                                                                                                                                           |
| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Name**            | Descriptive name that identifies the allocation purpose.                                                                                                              |
| **Description**     | Optional context about the allocation's purpose, focus areas, or evaluation priorities.                                                                               |
| **Date Range**      | Date range for the interactions to evaluate.                                                                                                                          |
| **Evaluation Form** | Form that guides auditors during review. Also determines which queues appear in subsequent filters.                                                                   |
| **Languages**       | Languages to include. Select specific languages for language-specific audits, or select all for full coverage. The system shows the total matching interaction count. |
| **Queue**           | Queue associated with the selected evaluation form.                                                                                                                   |

<img src="https://mintcdn.com/koreai-agent-management-platform-dev/wxwjoU2iOkCQKGUR/ai-for-service/quality-ai/analyze/allocations/images/queue-selection.png?fit=max&auto=format&n=wxwjoU2iOkCQKGUR&q=85&s=6933306cd385f31267f0337ba63fbfdc" alt="Queue Selection" width="454" height="273" data-path="ai-for-service/quality-ai/analyze/allocations/images/queue-selection.png" />

### Filter by Agents or Agent Groups

Narrow the scope to specific agents or groups:

| Filter           | How to use                                                                                                                             |
| ---------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| **Agents**       | Select individual agents from the dropdown. Leave empty to include all agents in the selected queues.                                  |
| **Agent Groups** | Select pre-configured groups for bulk selection. Useful for team-based evaluations. Combine with individual agent selection as needed. |

<img src="https://mintcdn.com/koreai-agent-management-platform-dev/wxwjoU2iOkCQKGUR/ai-for-service/quality-ai/analyze/allocations/images/agents-and-agent-groups-selection.png?fit=max&auto=format&n=wxwjoU2iOkCQKGUR&q=85&s=6bcc2bc4e7f60a633d242954a3d45dbf" alt="Agent and Agent Groups Selection" width="462" height="646" data-path="ai-for-service/quality-ai/analyze/allocations/images/agents-and-agent-groups-selection.png" />

The interaction count updates automatically as you adjust selections.

Select **Next** to proceed to the Allocation step.

***

## Step 2: Allocation Type

Choose how to select interactions from the filtered pool.

<img src="https://mintcdn.com/koreai-agent-management-platform-dev/wxwjoU2iOkCQKGUR/ai-for-service/quality-ai/analyze/allocations/images/allocation-type.png?fit=max&auto=format&n=wxwjoU2iOkCQKGUR&q=85&s=42039b4a846c713e2faa6fccf905c179" alt="Allocation Type" width="639" height="375" data-path="ai-for-service/quality-ai/analyze/allocations/images/allocation-type.png" />

### Random Allocation

Uses statistical sampling for impartial interaction selection. Ideal for representative coverage across agents.

<img src="https://mintcdn.com/koreai-agent-management-platform-dev/wxwjoU2iOkCQKGUR/ai-for-service/quality-ai/analyze/allocations/images/random-allocation.png?fit=max&auto=format&n=wxwjoU2iOkCQKGUR&q=85&s=445531a0b895357bdf604410a1781b56" alt="Random Allocation" width="643" height="909" data-path="ai-for-service/quality-ai/analyze/allocations/images/random-allocation.png" />

1. Select **Random**.

2. Enable the channels to include: **Voice**, **Chat**, or both.

3. Select an **Assignment Logic**:

   | Logic                      | Description                                                                                          |
   | -------------------------- | ---------------------------------------------------------------------------------------------------- |
   | **Percentage Per Agent**   | Allocates a consistent percentage of each agent's interactions. Ensures proportional representation. |
   | **Interactions Per Agent** | Assigns a fixed number of interactions per agent. Provides uniform sample sizes.                     |

4. Enter the percentage or interaction count. The system displays:
   * **Average per Agent**: Equivalent value in the opposite metric.
   * **Total Interactions**: Real-time total for this configuration.

### Custom Allocation

Lets you apply specific filters to target particular scenarios, sentiment ranges, or performance metrics. Ideal for focused evaluations or validating Auto QA accuracy.

<img src="https://mintcdn.com/koreai-agent-management-platform-dev/wxwjoU2iOkCQKGUR/ai-for-service/quality-ai/analyze/allocations/images/custom-allocation.png?fit=max&auto=format&n=wxwjoU2iOkCQKGUR&q=85&s=99c19cde1f96786d60598d84fefdc59b" alt="Custom Allocation" width="640" height="903" data-path="ai-for-service/quality-ai/analyze/allocations/images/custom-allocation.png" />

1. Select **Custom**.
2. Choose how to define your criteria:

   | Method           | When to use                                                                                |
   | ---------------- | ------------------------------------------------------------------------------------------ |
   | **Saved Filter** | Select a filter previously saved in Conversation Mining. Best for recurring audit focuses. |
   | **Quick Filter** | Configure a filter directly in the allocation workflow. Best for one-time allocations.     |

   <img src="https://mintcdn.com/koreai-agent-management-platform-dev/wxwjoU2iOkCQKGUR/ai-for-service/quality-ai/analyze/allocations/images/custom-quick-filter.png?fit=max&auto=format&n=wxwjoU2iOkCQKGUR&q=85&s=31d49e9bcede34e126b73c334dcd3272" alt="Custom Quick Filter" width="637" height="487" data-path="ai-for-service/quality-ai/analyze/allocations/images/custom-quick-filter.png" />

#### Quick Filter Creation

Select **Create Filter** to open the quick filter builder.

<img src="https://mintcdn.com/koreai-agent-management-platform-dev/wxwjoU2iOkCQKGUR/ai-for-service/quality-ai/analyze/allocations/images/quick-filters.png?fit=max&auto=format&n=wxwjoU2iOkCQKGUR&q=85&s=b94a07bc40e7c12e847e90a8ffbb9689" alt="Quick Filter Creation" width="657" height="906" data-path="ai-for-service/quality-ai/analyze/allocations/images/quick-filters.png" />

| Filter Category | What you can filter                                                                              |
| --------------- | ------------------------------------------------------------------------------------------------ |
| **Experience**  | Sentiment trends, emotions, wait time, CSAT, intents, topics, churn risk.                        |
| **Behavior**    | Evaluation metrics, empathy score, crutch word usage, playbook adherence, Kore Evaluation Score. |
| **Keyword**     | Include or exclude interactions containing specific words or phrases.                            |
| **Efficiency**  | AHT, handling time ranges, AHT deviation, number of transfers.                                   |

The interaction count updates dynamically as you adjust filters.

#### Per-Agent Control

After defining filters, you can further refine by sampling per agent:

* Specify a percentage or interaction count per agent within the filtered set.
* Combine targeted filtering with proportional sampling for precise control.

**Example**: Filter for interactions with sentiment scores less than 3, then sample 5% per agent from those results to focus on low-satisfaction situations.

Select **Next** to proceed to the Assignment step.

***

## Step 3: Assignment

Distribute the selected interactions across your auditor team.

<img src="https://mintcdn.com/koreai-agent-management-platform-dev/wxwjoU2iOkCQKGUR/ai-for-service/quality-ai/analyze/allocations/images/assignment.png?fit=max&auto=format&n=wxwjoU2iOkCQKGUR&q=85&s=0e7b519f78c2ef265a7e958f42f667e2" alt="Assignment" width="634" height="904" data-path="ai-for-service/quality-ai/analyze/allocations/images/assignment.png" />

1. Use the **Search Auditors** dropdown to select team members.

2. Choose multiple auditors to distribute the workload.

3. Enter the **Allocation Percentage** for each auditor. The system calculates the exact interaction count per auditor automatically.

   **Example** (100 total interactions, 3 auditors):

   * Auditor A: 40% = 40 interactions
   * Auditor B: 30% = 30 interactions
   * Auditor C: 30% = 30 interactions

4. Adjust percentages until they total exactly 100%. The **Create** button remains disabled until the total reaches 100%.

5. Review the complete configuration:
   * **Settings**: Form, languages, agents, agent groups.
   * **Allocation**: Method (Random or Custom), filters, total interactions.
   * **Assignment**: Auditors and their percentages.

6. Select **Create** to activate the allocation.

The system immediately assigns interactions to auditors. Auditors can see their assignments in the **Assigned to Me** tab right away.

### After Creating an Allocation

* The allocation appears in your **My Allocations** tab.
* Auditors see their assigned interactions in **Assigned to Me**.
* Track completion progress in real-time.
* Edit the allocation at any time to reassign pending interactions.

***

## Use Case: Managing Auditor Availability During Peak Season

**Scenario**: A QA Manager creates a monthly random sample allocation for 15 auditors. Three days later, two auditors report unexpected leave, leaving 40 pending interactions unassigned.

### Step-by-Step Resolution

1. **Identify the issue**
   * Open **My Allocations** tab.
   * Locate the "December 2024 Monthly Sample" allocation.
   * Confirm that two auditors (John, Doe) have 0 interactions completed and 20 pending each.

2. **Access Edit**
   * Select **Edit** from the Actions menu.
   * Review: Auditor John — 20 assigned, 0 completed, 20 pending. Auditor Doe — 20 assigned, 0 completed, 20 pending.

3. **Reassign pending work**
   * Select the checkboxes for Auditor John and Auditor Doe (40 total pending interactions).
   * Select **Add New Auditors** and choose three auditors with lighter workloads: C, P, R.

4. **Configure new distribution**
   * C: 35% = 14 interactions
   * P: 35% = 14 interactions
   * R: 30% = 12 interactions
   * Verify the total reaches 100%.

5. **Complete reassignment**
   * Select **Update**.
   * C, P, and R immediately see new assignments in **Assigned to Me**.
   * Completed work from original auditors remains unchanged.

**Outcome**: The monthly audit stays on schedule. No interactions are lost or duplicated, and workload is balanced across available team members.

***


Built with [Mintlify](https://mintlify.com).