The AgentivUse cases

Hear the bad review before it goes public

An agent that asks each customer for a one tap rating on LINE after the job is done, thanks the happy ones and alerts the owner to the unhappy ones with a drafted reply

Function: Customer serviceEffort: About a weekPublished: 2026-10-20

The problem

A clinic, salon, repair shop or delivery business only learns a customer was unhappy when the review appears on Google Maps or Facebook. Asking everyone by hand does not happen, and paper feedback forms end up in a drawer.

How the agent works

  1. It starts

    When a booking or order is marked complete in the shop's sheet or booking system, the agent waits a set time (two hours for a salon, next morning for a delivery) and sends one push message from the LINE OA to that customer: a short Thai or English question with five quick reply buttons for the rating and one for skip.

  2. The agent works

    The tap comes back as a postback through the webhook; the agent logs the rating, the service and the staff member to a Google Sheet, with no typing from the customer. Four or five stars get a thank you and, if the owner wants, a review link; three stars and below trigger one follow up question in the chat (what should we have done better) and an immediate alert to the owner's LINE group with the customer's answer, a drafted apology and a make good offer. The owner edits and sends the reply from the LINE OA chat; the agent never sends apologies or offers on its own.

  3. The result

    A weekly summary shows the average rating per service and per staff member.

Worked example

LINE's Messaging API spec covers the pieces: a push message can be sent to a user at any time with up to five message objects, each message can carry a quick reply with up to 13 buttons, and a postback action returns up to 300 characters of data to your webhook without the customer typing. The Python SDK's README shows webhook signature checks and replies, and its MessagingApi reference lists push_message, narrowcast and get_message_quota, which matters because push messages count against the OA's monthly message quota. LINE publishes no response rates, so track the share of customers who tap and the average rating from your own sheet.

PDPA note. Ratings are tied to LINE user IDs. Store only the user ID, rating, service and date, not names or phone numbers; say in the shop's privacy notice that a feedback message follows each visit, and stop sending the moment a customer asks.

Join the Agent OS Club

8 weeks to the AI team a 50 person company would hire. Instant access to our agent blueprints. USD 15 a month, cancel any time.

Join the Agent OS Club

Building this for an organization? Learn more at theagentiv.com

Sources

Related use cases

Every Shopee review answered, in your voice

An agent that reads new Shopee and Lazada reviews each morning, drafts a reply to each in the shop's tone and posts them after the owner approves

Customer serviceEffort: About a weekShopee · Lazada · Claude

Reviews pile up across two seller centres and most go unanswered, while the one star review with a shipping complaint sits in public for days. Replying by hand means copying the same thank you note forty times and still missing the one that needed a real answer.

Your LINE OA takes the bookings

A LINE Official Account assistant that takes bookings in chat, checks Google Calendar, confirms the slot and sends a reminder the day before

Customer serviceEffort: About a weekLINE · Google Calendar · Gemini

Salons, clinics, restaurants and repair shops in Thailand take bookings through LINE chat, so a staff member reads every message, checks the paper book or calendar, types a reply and later remembers to send a reminder. Evenings and busy hours leave customers waiting, double bookings happen, and no-shows cost the slot.

Your LINE OA answers the same five questions

An agent that answers FAQs and order status on your LINE Official Account and hands the rest to staff

Customer serviceEffort: About a weekLINE · Claude · Slack

Most LINE OA chats ask the same five things: price, stock, shipping time, where my order is, and how to pay. Admins answer them one by one until late evening, and the one message that really needs a person, a complaint or a refund, waits in the same queue.