Support ticket triage

Route a backlog of support tickets by category and urgency, and flag the angry customers and refund requests.

Run this on your file Download the template CSV

Columns to upload

Name the columns in your CSV like this. Extra columns are fine: every column of the row is sent with the questions.

Column	What it holds
`ticket_id`	Ticket ID
`subject`	Ticket subject
`body`	First message from the customer

Questions

Each question adds a column to your file. The answer is one of the listed values, or Unsure when the model's confidence is below the cutoff: 70% for pick-one and scale questions, 80% for yes or no.

New column	Question	Possible answers
`category`Pick one	What is the ticket about?	billing Charges, invoices, payment methods order Delivery, missing or damaged items account Login, password, account settings bug Something on the site or app is broken how-to Asks how to do something cancel Wants to cancel or pause other Praise, gifts or anything else
`urgency`Scale	How urgent is the ticket?	low a question or praise, no deadline normal a problem that does not stop the customer high blocks an order, a delivery, a login or a payment urgent money taken by mistake, or a threat to leave or dispute a charge Lowest to highest
`angry`Yes or no	Is the customer angry or threatening to leave?	yes The customer is angry or threatens to leave or dispute a charge no The customer is calm
`refund`Yes or no	Does the customer ask for a refund or credit?	yes They ask for money back or a credit no They do not

Example row

Column	Value
`ticket_id`	48213
`subject`	Charged twice!!
`body`	You charged my card twice for the September box. Refund the second one today or I'm disputing it with my bank.

Answers from a test run on this row

Column	Answer	Confidence
`category`	billing	100%
`urgency`	urgent: money taken by mistake, or a threat to leave or dispute a charge	100%
`angry`	yes	97%
`refund`	yes	99%

More support use cases

Use case	What it does	New columns
Chat transcript quality review	Review support chats for resolution and agent tone without reading every transcript.	`resolved` `agent_tone` `escalated` `customer_repeated`
Customer satisfaction comments	Find out whether low satisfaction scores are about the agent, the product or the policy.	`about` `sentiment` `agent_praised`
Bug report labeling	Label incoming bug reports by product area and severity, and send back the ones with no steps to reproduce.	`area` `severity` `repro_steps` `money_or_data`
Help center gaps	Match customer questions to your help articles and list the questions no article answers.	`article_answers` `self_serve` `question_type`
Cancellation reasons	Code why subscribers cancel and find the ones a pause or a discount could keep.	`reason` `pause_would_help` `price_sensitive`