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

# OPIC 1.0

> Operations Intent Classifier version 1.0 - Production-ready intent classification model

## Overview

OPIC 1.0 is the first production release of the Operations Intent Classifier. This model provides accurate multi-class intent classification specifically tuned for ecommerce customer support scenarios.

## What's New in 1.0

* **10 Intent Classes**: Comprehensive coverage of common ecommerce support intents
* **Sub-60ms Latency**: Optimized for real-time inference
* **Batch Processing**: Support for classifying multiple messages in a single request
* **Confidence Thresholds**: Configurable filtering of low-confidence predictions

## Model Specifications

| Property         | Value                                    |
| ---------------- | ---------------------------------------- |
| Model Version    | 1.0.0                                    |
| Architecture     | Fine-tuned BERT-based transformer        |
| Training Data    | Ecommerce customer support conversations |
| Intent Classes   | 10                                       |
| Max Input Length | 2,048 characters                         |
| Languages        | English                                  |
| Average Latency  | \< 60ms (p95)                            |

## Supported Intents

| Intent            | Description                       |
| ----------------- | --------------------------------- |
| `track_order`     | Order/shipment tracking inquiries |
| `cancel_order`    | Order cancellation requests       |
| `return_item`     | Product return inquiries          |
| `refund_request`  | Refund status or requests         |
| `product_inquiry` | Product questions                 |
| `change_address`  | Delivery address modifications    |
| `payment_issue`   | Payment problems                  |
| `complaint`       | Negative feedback                 |
| `compliment`      | Positive feedback                 |
| `other`           | Unclassified intents              |

## Quick Start

### Single Message Classification

```bash theme={null}
curl -X POST 'https://api.usehandled.io/api/v1/ipaas/inference/intent-classify' \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Content-Type: application/json' \
  -d '{
    "message": "Where is my order?",
    "model_version": "1.0.0"
  }'
```

### Response

```json theme={null}
{
  "request_id": "req_abc123",
  "message": "Where is my order?",
  "predictions": [
    {
      "intent": "track_order",
      "confidence": 0.95
    }
  ],
  "top_intent": "track_order",
  "latency_ms": 42,
  "model_version": "1.0.0"
}
```

## Best Practices

1. **Use confidence thresholds**: Set `threshold` to filter out low-confidence predictions
2. **Request top-k results**: Use `top_k` to get multiple intent predictions for ambiguous messages
3. **Batch when possible**: Group multiple messages to reduce API calls

## Migration Notes

OPIC 1.0 is the initial release. Future versions will maintain backward compatibility with the 1.x API contract.