Help center gaps

Match customer questions to your help articles and list the questions no article answers.

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
`question`	The customer's question
`article_title`	Title of the help article your search returned
`article_summary`	First lines of that article

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
`article_answers`Yes or no	Does the article answer the customer's question?	yes The article covers what the customer asked no The article is about something else, or only part of it
`self_serve`Yes or no	Could the customer solve this alone with the right article, without an agent?	yes Instructions alone would solve it no It needs an agent to act on the account
`question_type`Pick one	What kind of question is it?	how-to How to do something policy What the rules are status Where an order or request stands problem Something went wrong

Example row

Column	Value
`question`	Can I change the address for just one shipment?
`article_title`	Updating your account details
`article_summary`	Change your name, email or default shipping address from the Account page.

Answers from a test run on this row

Column	Answer	Confidence
`article_answers`	no	89%
`self_serve`	no	83%
`question_type`	Unsure	34%

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`
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`
Cancellation reasons	Code why subscribers cancel and find the ones a pause or a discount could keep.	`reason` `pause_would_help` `price_sensitive`