How is intent classification different from intent detection?

They're often used interchangeably. Technically, intent detection is the broader process of determining whether and what intent is present; intent classification is the specific task of assigning a category label. In practice, most AI support tools combine both in a single classification step.

How many intent categories should I define?

Enough to drive different downstream behaviors, but no more. If 'return request' and 'exchange request' route to the same workflow, they probably don't need to be separate intents. If they trigger different responses and different actions, separate them. Start with 10–15 and add granularity only where it changes what the AI does.

What's the impact of a wrong intent classification?

The response generated from the wrong intent is nearly always wrong too. The customer sees a response that doesn't address what they asked, leading to a follow-up message, frustration, and often an escalation. Every misclassification costs more than it saved in automation.

Glossary

Intent Classification

Intent classification is the AI task of automatically assigning an incoming customer message to one of a predefined set of intent categories — such as 'order tracking,' 'refund request,' or 'product question' — based on the message's meaning, enabling downstream routing, response selection, and action triggering.

Book a demo See pricing

What it means

Key insight

Intent classification is the traffic controller of customer support AI — get it right and everything downstream flows; get it wrong and every subsequent step compounds the error.

Every incoming customer message must be understood before it can be handled. Intent classification is the formal AI task of assigning that understanding: given this message, which category of customer need does it represent? In ecommerce support, intents map to operational workflows: a 'return initiation' intent triggers the return eligibility check workflow; a 'shipping status' intent triggers an order lookup; a 'product question' intent retrieves relevant product catalog content. Classification can be binary (is this a refund request or not?) or multi-class (which of 20 intent categories does this belong to?) and can handle multi-intent messages where a single customer message expresses more than one underlying need. Modern LLM-based classifiers greatly outperform the older intent-slot models by understanding meaning and context rather than keyword patterns — enabling much higher accuracy on the wide variety of ways customers express the same underlying need.

Why it matters

Intent classification accuracy is the single most impactful variable in AI support quality. Misclassify a refund request as a product question and the customer receives a response about the product instead of about their money — a frustrating experience that typically escalates. For Shopify merchants, the most important intents by volume are consistent across stores: order tracking, return initiation, refund status, shipping delay, product inquiry, and discount code use. Getting classification right for those five or six categories handles the vast majority of support volume and delivers the largest impact on resolution rates.

How Bookbag helps

Pre-Built Ecommerce Intent Library

Bookbag ships with a high-accuracy intent classification model pre-trained on ecommerce support conversations, covering the 20+ most common Shopify support intents out of the box.

Custom Intent Extension

Merchants add brand-specific intents — subscription management questions, loyalty program inquiries, custom product configuration — and provide training examples for Bookbag to learn from.

Multi-Intent Detection

When a customer message contains more than one need ('I want to return this and also ask about the replacement product'), Bookbag classifies all intents present and addresses each in sequence rather than picking just one.

Frequently Asked Questions

See Bookbag in action

Join the ecommerce teams resolving more tickets, answering 24/7, and turning support into a revenue channel with Bookbag.