Skip to content

See which customers are upset before you open a single ticket

The Replyco ticket list with a red, yellow or green face in the Tone column of every scored ticket. The red frown on the ticket "Received the 4-in-1 hub instead of the 7-in-1" is highlighted and has opened a card: "Customer tone:" Upset 0.28, with the AI's reason "Matter-of-fact; mildly frustrated by the wrong item."

In a ticket list, a customer chasing a refund for the third time looks exactly like one asking a calm first question. Replyco now reads the tone of every incoming customer message, scores it from 0 (furious) to 1 (delighted), and shows your team the mood before anyone opens the ticket.

  • A face on every ticket. The new Tone column in the ticket list shows a red, yellow or green face for each ticket’s latest scored customer message, so your team spots upset customers at a glance.
  • The reason, not just the score. Hover a face for the score and a one-line reason from the AI, such as Frustrated about late delivery and broken item; demands replacement., so you know what went wrong before you read the thread.
  • Upset customers move up the queue. Tone rules turn score ranges into your SLA priorities, so a furious message can make its ticket your most urgent one, with that priority’s response deadline. You decide whether tone may also replace a priority someone already set.
  • Your rules can react. Tone score (0 = furious, 1 = delighted) is a new condition in message rules, so an angry message can go straight to a senior agent or get a label.
  • See which products upset customers. The Average tone by product widget on the Overview dashboard ranks products by the average tone of their tickets, worst first.
The Not Resolved ticket list in Replyco with a coloured face in the Tone column of every scored ticket: yellow and green faces for calm and happy customers, and one red frown, highlighted, on the ticket "Received the 4-in-1 hub instead of the 7-in-1" from Daniel Hughes. The red face has opened a card that reads "Customer tone:" with the band Upset and the score 0.28, and below it the AI's reason: "Matter-of-fact; mildly frustrated by the wrong item." One row has no face because none of its messages was scored.
One look at the list shows who is upset, and the card says why.
What this screenshot shows
Screen
Not Resolved (/tickets/notresolved)
Highlighted
img “Upset”, tone-column, focused. shows the tone card: band, score, reason
Also visible
Tone column with red, yellow and green faces; card: Customer tone: Upset 0.28; reason: Matter-of-fact; mildly frustrated by the wrong item.
Purpose
tone detection in the ticket list

The customers who wait angry are the ones who open disputes and leave one-star reviews, and nothing in a subject line gives them away. Tone detection finds them for you, so they are answered first without anyone reading every message to look for them. Every priority tone assigns leaves a row in the ticket’s history with the score and the AI’s reason, so a surprising Urgent can always be explained.

Ticket #32533 in Replyco with its conversation in the middle: the customer's first message at 04:49 with a yellow face and the follow-up "Any update on this, please?" at 04:58 with a red face. Below the follow-up, a grey history row is highlighted. It reads "Tone score 0.28 assigned priority Urgent (Matter-of-fact; mildly frustrated by the wrong item.)" with its date underneath. The priority field at the top of the right-hand panel shows Urgent, the priority tone assigned.
When tone sets a priority, the ticket's history says which score and which reason did it.
What this screenshot shows
Screen
Respond (/ticket/:threadId)
Highlighted
paragraph “Tone score {{score}} assigned priority {{priority}} ({{reason}})”, conversation, visible. records the tone-assigned priority with score and reason
Also visible
history row: Tone score 0.28 assigned priority Urgent (reason); priority field: Urgent; two customer messages with yellow and red faces
Purpose
tone-driven SLA priority, with its audit row
  1. Go to ToolsAI Settings, switch on Message Tone Analysis on the General tab and select Save. New customer messages are scored from now on; nothing is prioritised yet.

  2. Watch the Tone column for a week and hover a few faces to read the reasons. If your customers write in a way the AI misreads, add a few examples of your own on the Tone tab.

  3. When the scores look right, tick Let tone set the SLA priority on the Tone tab and add tone rules, for example 0.00–0.30 → Urgent. Tone then gives a priority to tickets that have none.

Every step and every switch is explained in Setting it up in five steps.

Tone detection is part of Replyco AI, which every plan includes; during a trial every feature is on. It stays off until someone with the Admin permission with Edit rights switches it on. Letting tone set priorities uses your priorities under AdminCompany Settings › Priorities & SLA, which every current plan includes. Messages are scored in the language the customer wrote, without translation; conversations under Chats are not scored. Each scored message is one AI action, listed as Tone Analysis under AdminBilling › AI Usage.