Automated Customer Feedback Theme Analysis
When you hand over a feedback export, WebRun opens ChatGPT, pastes the comments into a project chat, prompts it to cluster the comments into themes ranked by how often they appear with verbatim quotes attached, posts the ranked themes to Slack, and texts the owner by Twilio that the read is ready.
How do I turn a pile of customer feedback into ranked themes?
When you upload a customer feedback export, WebRun attaches it to a ChatGPT project chat and prompts it to cluster the comments into themes ranked by frequency with verbatim quotes. It posts the ranked themes to Slack and texts the review owner by Twilio, so meetings argue about priorities instead of reading raw comments.
- A review meeting starts from themes, not raw comments
- Every theme is backed by quotes you can check
- Unclassifiable comments are surfaced instead of dropped
Built for product managers · support leads · UX researchers · founders
What does WebRun do on every run?
The exact actions WebRun takes, in order - in plain language, so you can adjust anything.
-
WebRun signs in and gets to work
Opens
chatgpt.comin a real browser with your saved login - no setup, no API keys. -
1
ChatGPT - cluster the feedback into themes
chatgpt.com
WebRun opens ChatGPT to cluster the feedback into themes. - Open ChatGPT and start a chat in the project you keep feedback work in
- Paste the feedback comments you provided for this run into the chat
- Prompt it to group the comments into themes and rank them by how many comments fall under each
- Ask for two or three verbatim quotes per theme and a one-line description, and tell it to say when a comment fits nothing
Done when The chat has returned ranked themes with counts and quotes for each.
-
2
Slack - post the ranked themes
slack.com
WebRun opens Slack to post the ranked themes. - Post the ranked themes to your product channel, biggest first
- Show the comment count and one representative quote under each theme
- List the comments that did not fit a theme separately so nothing is quietly dropped
- Link the chat so anyone can read the full working
Done when The ranked themes with quotes are in Slack ready for review.
-
3
Twilio - text the owner it is ready
twilio.com
WebRun opens Twilio to text the owner it is ready. - Send one short text to the person who owns the review, telling them the analysis is ready
- Include the theme count and the biggest theme in the message
- Keep the recipient list to the internal owners you configured. WebRun never texts a customer
Done when The review owner has been told the themes are ready to read.
How is each run configured?
Secure by default
Connect once, stays signed in
WebRun signs in once and keeps each session in a persistent environment, so every run picks up right where it left off.
Every action is checked against this policy before it runs.
Questions, answered
Does it message customers about their feedback?
No. The only text WebRun sends goes to the internal owners you list, telling them the analysis is ready. Customers are never contacted and their comments are never replied to from this workflow.
Will it invent themes that are not in the data?
Every theme carries verbatim quotes from your file so you can check it. Comments that fit no theme are listed separately rather than forced into a bucket, so nothing is silently reshaped.
What kind of feedback can it read?
Any text feedback you hand over, such as survey answers, support ticket comments, or review text. WebRun pastes it into the chat rather than attaching a file, so the prompt is the same whatever the source.
Related templates
Put this on autopilot.
Turn it on in minutes - or have our team set it up for you.