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

# Tagging & Classification Overview

> Automatically organize and analyze conversations

Duckie automatically classifies conversations using categories, attributes, and resolution rules — giving you structured data for analysis and reporting.

{/* Screenshot: Tag section showing categories, attributes, and resolution in nav */}

## Why Classification Matters

Classification transforms unstructured conversations into actionable data:

| Benefit                 | Example                                        |
| ----------------------- | ---------------------------------------------- |
| **Understand trends**   | "40% of tickets are billing-related"           |
| **Measure performance** | "Technical issues have 85% resolution rate"    |
| **Route intelligently** | "High-priority tickets go to senior agents"    |
| **Improve over time**   | "Most escalations happen in shipping category" |

## Classification Components

### Categories

High-level, mutually exclusive conversation types:

```
├── Billing
├── Technical Support
├── Account Issues
├── Feature Requests
└── General Inquiry
```

Each conversation gets **one** category.

### Attributes

Custom fields with predefined options:

| Attribute         | Options                     |
| ----------------- | --------------------------- |
| **Priority**      | High, Medium, Low           |
| **Product Area**  | Dashboard, API, Mobile App  |
| **Customer Tier** | Enterprise, Pro, Free       |
| **Sentiment**     | Positive, Neutral, Negative |

Conversations can have **multiple** attributes.

### Resolution Rules

Conditions that determine when a conversation is "resolved":

* Customer confirmed the issue is fixed
* No response needed (informational)
* Time elapsed without follow-up

## How Classification Works

At the end of each agent run:

```
Conversation ends
       │
       ▼
┌─────────────────────┐
│ Assign Category     │ → "Billing"
└─────────────────────┘
       │
       ▼
┌─────────────────────┐
│ Extract Attributes  │ → Priority: High
└─────────────────────┘   Product: API
       │
       ▼
┌─────────────────────┐
│ Evaluate Resolution │ → Resolved: Yes
└─────────────────────┘
```

The AI analyzes the conversation context and applies appropriate classifications.

## Using Classification Data

### In Analytics

View breakdowns by category and attribute:

{/* Screenshot: Analytics breakdown showing category pie chart and attribute bars */}

### In Run History

Filter and search by classification:

{/* Screenshot: Run history with category and attribute filter dropdowns */}

### For Routing (Future)

Use classification for intelligent routing based on category or attributes.

## Getting Started

<Steps>
  <Step title="Create Categories">
    Define the high-level conversation types for your business.
  </Step>

  <Step title="Create Attributes">
    Add custom fields for the dimensions you want to track.
  </Step>

  <Step title="Configure Resolution">
    Define what "resolved" means for your team.
  </Step>

  <Step title="Assign to Agents">
    Select which categories and attributes each agent should apply.
  </Step>
</Steps>

## Next Steps

<CardGroup cols={2}>
  <Card title="Categories" icon="folder" href="/tagging/categories">
    Set up conversation categories
  </Card>

  <Card title="Attributes" icon="tags" href="/tagging/attributes">
    Create custom attributes
  </Card>

  <Card title="Resolution Rules" icon="circle-check" href="/tagging/resolution-rules">
    Define what "resolved" means
  </Card>

  <Card title="Analytics" icon="chart-pie" href="/analytics/breakdown">
    Analyze by classification
  </Card>
</CardGroup>