How many intents should a support AI cover?

Start with your top 10–15 intents by volume — they typically account for 80%+ of all tickets. Adding more intents beyond that has diminishing returns and risks over-segmenting categories that are better handled with a single flexible intent.

What happens when a customer message contains multiple intents?

Good support AI detects multi-intent messages and either handles them sequentially or addresses the primary intent first while noting the secondary. Bookbag extracts all intents from a message to ensure nothing is missed.

How is intent detection different from keyword matching?

Keyword matching triggers on specific words; intent detection understands meaning. A keyword system misses "my package is lost" if it only looks for "tracking." Intent detection correctly classifies it as a tracking/lost shipment request regardless of exact wording.

Glossary

Intent Detection

Intent detection is the AI process of classifying an incoming customer message into one of a set of possible goals or purposes — such as "track order," "request refund," or "ask product question" — so the system can route the conversation to the appropriate response or action.

Book a demo See pricing

What it means

Key insight

Getting the intent right on the first message is what separates a support AI that resolves issues from one that frustrates customers.

Intent detection is the decision-making backbone of a support AI. Every incoming message must be classified: what does this customer want? In traditional chatbot frameworks, intents were hand-labeled categories with manually curated example phrases. Modern LLM-based systems infer intent from context and meaning, making them much more robust to the variety of ways customers express the same underlying need. Accurate intent detection directly drives downstream quality: get the intent right and the rest of the conversation flows logically; misclassify it and every subsequent step is wrong. In ecommerce, the most common high-volume intents — order tracking, return initiation, refund status, product inquiry — can be detected with high accuracy because they have clear linguistic signals, even when customers phrase them in unexpected ways.

Why it matters

Intent detection accuracy is the single biggest lever for improving AI support quality. Each misclassified intent is a broken support interaction. For high-volume Shopify stores handling thousands of conversations daily, even a 5% improvement in intent detection accuracy prevents hundreds of failed interactions per day — reducing escalations, cutting handle time, and improving CSAT scores directly.

How Bookbag helps

Shopify-Tuned Intent Library

Bookbag ships with a pre-built intent library tailored to ecommerce support — covering order tracking, returns, refunds, product questions, shipping issues, and more — with high out-of-the-box accuracy.

Custom Intent Training

Merchants can add custom intents specific to their store — subscription management, loyalty points, product customization questions — and provide example phrases for Bookbag to learn from.

Fallback on Low Confidence

When intent confidence falls below threshold, Bookbag asks a clarifying question rather than proceeding with a guess, ensuring misclassifications don\'t cascade into wrong resolutions.

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.