Customer satisfaction comments

Find out whether low satisfaction scores are about the agent, the product or the policy.

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
`rating`	CSAT rating
`comment`	The customer's comment
`agent`	Agent who handled the ticket

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

New column	Question	Possible answers
`about`Pick one	What is the comment mainly about?	agent The person who helped them product The product itself wait time How long it took to get help policy A rule: returns, refunds, shipping limits other Anything else
`sentiment`Scale	How does the customer feel?	very negative negative neutral positive very positive Lowest to highest
`agent_praised`Yes or no	Does the comment praise the agent?	yes It says something good about the agent no It does not

aboutPick one

What is the comment mainly about?

agent The person who helped them
product The product itself
wait time How long it took to get help
policy A rule: returns, refunds, shipping limits
other Anything else

sentimentScale

How does the customer feel?

very negative
negative
neutral
positive
very positive

Lowest to highest

agent_praisedYes or no

Does the comment praise the agent?

yes It says something good about the agent
no It does not

Example row

Column	Value
`rating`	2
`comment`	Ana was lovely but a 30 day return window on unopened wine is ridiculous.
`agent`	Ana

Answers from a test run on this row

Column	Answer	Confidence
`about`	policy	100%
`sentiment`	negative	97%
`agent_praised`	yes	95%

More support use cases

Use case	What it does	New columns
Support ticket triage	Route a backlog of support tickets by category and urgency, and flag the angry customers and refund requests.	`category` `urgency` `angry` `refund`
Chat transcript quality review	Review support chats for resolution and agent tone without reading every transcript.	`resolved` `agent_tone` `escalated` `customer_repeated`
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`