How accurate is Bookbag's intent classification?

Across standard ecommerce intent types, Bookbag achieves over 92% intent classification accuracy. Accuracy is higher for common, clearly phrased intents and lower for ambiguous or highly novel message types.

Can I add custom intent types specific to my business?

Yes. Merchants can define custom intent categories — for example, a subscription brand might add 'pause subscription' or 'swap product' — and Bookbag will classify incoming messages against the extended taxonomy.

What happens when a customer's message has no clear intent?

Low-signal messages — complaints without a specific request, emotional venting — are classified as 'unknown intent' and routed to a human agent who can determine the appropriate response.

Glossary

Customer Intent

Customer intent is the underlying goal or request a customer is expressing in a support message — what they actually want done — as determined by AI classification of their words and context.

Book a demo See pricing

What it means

Key insight

Intent classification is the first step in every support decision. An AI that misclassifies intent will misroute, misprioritize, and misresolve the ticket — regardless of how good its resolution logic is.

In ecommerce support, intent classification is the process of reading a customer's message and determining what they want: to know their order status, to initiate a return, to request a refund, to cancel an order, to change a shipping address, to report a defective item, to leave feedback, and so on. This sounds straightforward, but natural language is messy. 'I need to send this back' means the same as 'how do I return this?' and 'I don't want it'. 'My package is taking forever' could be an order status request or a frustration expression that needs an empathetic response before any data lookup. Intent classification sits at the top of the resolution pipeline: get it right, and the rest flows efficiently; get it wrong, and every downstream step is solving the wrong problem. Good intent systems handle multi-intent messages ('I want to return item A and also update my address for the reshipment of item B'), low-signal messages ('I'm very unhappy'), and novel phrasings not in the training set.

Why it matters

Every support routing, prioritization, and resolution decision depends on knowing what the customer wants. For ecommerce AI, intent accuracy directly drives resolution accuracy and customer satisfaction. A misclassified intent that routes a refund request to the order status flow means the customer gets tracking information when they wanted their money back — a frustrating and trust-eroding experience. High intent accuracy is the foundation everything else is built on.

How Bookbag helps

Ecommerce-specific intent taxonomy

Bookbag's intent classifier is trained on ecommerce support conversations and recognizes the specific intent types relevant to Shopify brands — order status, returns, refunds, cancellations, product questions, complaints, and more.

Multi-intent detection

When a single message contains multiple requests, Bookbag identifies each intent separately and handles them in sequence or parallel, rather than arbitrarily picking one and ignoring the rest.

Low-confidence fallback routing

When intent confidence falls below a configurable threshold, Bookbag routes the ticket to a human agent rather than attempting a resolution on a misclassified intent.

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.