WhatsApp order-status assistant for a D2C brand
How we would take “where is my order?” messages off a small support team and answer them in seconds.
An example project. Company details are illustrative.
Targets we set for this kind of project
- Share of order-status queries answered without a person
- Target 60%
- Target first-response time for order queries
- Hours → under 1 minute
- Support time to be measured before and after
- Baseline first
Client context
A direct-to-consumer skincare brand sells through its own Shopify store and ships across the UAE. Two people handle customer support over WhatsApp and email alongside other duties.
Problem
Most incoming messages ask the same thing: where is my order? Each one means opening the store admin, finding the order, checking the courier site and typing a reply. During sale periods the queue builds up, replies slow down and customers message again, which adds to the queue.
Approach
- Measure first. Export a month of conversations and tag them by type to confirm how many are order-status queries and how long each takes.
- Start narrow. Automate only order status in the first release, and leave returns, complaints and product advice with the team.
- Design the handover. Agree exactly when a person takes over: delayed orders, failed deliveries, anything the assistant cannot match to an order.
- Test with real messages. Replay past conversations through the assistant before any customer sees it.
Solution
- The customer messages the brand's WhatsApp number.
- The assistant identifies the order from the phone number, or asks for the order ID.
- It reads the order from Shopify and the latest scan from the courier.
- It replies in plain language with the status and a tracking link.
- If the order is delayed beyond the agreed threshold, or the customer is unhappy, the conversation is passed to the support team with a short summary.
- Every conversation is logged to a sheet so the team can review what was asked and how it was answered.
Measurable results
Every project starts by recording a baseline, and results are reported against it. For this kind of project we measure:
- Share of order-status queries resolved without a person
- First-response time for order queries
- Support hours spent on order queries per week
- Number of conversations handed over, and why
Tools used
WhatsApp Business API, n8n, Shopify, the courier's tracking API and Google Sheets for the conversation log.