Tech

Intent Detection

Intent detection is the natural language processing task of identifying what a customer wants from a message, regardless of wording, dialect, or language. A Gulf Arabic phrase, a Modern Standard Arabic phrase, and an English sentence asking the same underlying question should all be classified as the same intent and routed to the same workflow.

Intent detection works by mapping the meaning of an incoming message to one of a defined set of categories the system knows how to act on - order tracking, refund request, appointment booking, and so on - rather than matching literal keywords. This requires the underlying language model to recognize paraphrase, sentence structure variation, and even spelling inconsistencies as expressions of the same underlying need. Accuracy is typically measured by how often the detected intent matches what a human reviewer would classify the message as.

In MENA markets, intent detection has to work across at least three simultaneous variations - Gulf Arabic, Modern Standard Arabic, and English - plus Arabizi and code-switched messages, since the same customer might type different phrasings of the same question depending on mood or habit. If the system only recognizes one register, it will fail to detect intent on a large share of real messages, driving unnecessary escalation and undermining first contact resolution across WhatsApp and other channels.

In Eshal: Eshal's intent detection is trained specifically on Gulf and Levantine Arabic alongside English and Arabizi, so it can map differently phrased or differently spelled messages to the same underlying workflow. This is the layer that lets the AI concierge route order-status style questions correctly regardless of dialect, which in turn supports Eshal's reported first contact resolution and average resolution rate performance.

FAQ

Common questions about Intent Detection

Intent detection is the process by which an AI system figures out what a customer wants from a message, no matter how it is phrased, spelled, or which language or dialect it is written in. It is the step that determines which workflow - like order tracking or refunds - a conversation gets routed to.
Arabic intent detection is harder because customers may write in Modern Standard Arabic, a regional dialect like Gulf or Levantine Arabic, Arabizi, or a mix of Arabic and English within a single message. Without dialect-aware training, a system may correctly detect intent in formal Arabic but fail on the colloquial phrasing customers actually use day to day.

See these concepts work in practice.

Book a 30-minute demo and see Eshal executing real Arabic and English customer workflows - live - for your exact industry.