# Turn new customer reviews into Linear issues every morning

> Every weekday we read your G2, Capterra, and Trustpilot pages, file what customers asked for in Linear, and post a short digest to Slack.

- Workflow type: agent
- Services: Hyperbrowser, Linear, Slack
- Categories: Product, Customer Support
- Published: 2026-08-07

## What it does

- Reads your public review pages every weekday morning and picks up only the reviews that landed since the last check.
- Groups the new reviews into themes and works out which are bugs, which are feature requests, and which are simply praise.
- Checks Linear before filing anything, so a recurring complaint adds a comment to the issue you already have instead of creating a duplicate. Anything rated three stars or below is flagged high priority.
- Posts one Slack digest with the review count, the average rating, the top themes with a real customer quote each, and links to every issue it touched. Quiet days stay quiet: no new reviews means no message.

## What you'll need

- A Hyperbrowser account, which is what reads the review pages for you
- A Linear workspace, and the team you want new issues filed into
- A Slack workspace and the channel where the digest should land
- The web addresses of the review pages you want watched, such as your G2, Capterra, and Trustpilot listings

## Prompt

Every weekday at 8am, read our public review pages, turn the new reviews into tracked product work in Linear, and post a short digest to Slack. Only reviews published since the previous run should be considered.

Keep the review page URLs as a configurable list at the top of the workflow so I can add or remove sites without rewriting anything. Start with our G2, Capterra, and Trustpilot listing pages.

Use Hyperbrowser's Start Extract Job across every configured review URL, with a schema that captures, for each review: reviewer name, publication date, star rating, headline, and body text. Then poll Get Extract Job Result until the job reports completed or failed. Review sites render their reviews client side and are aggressive about blocking automated traffic, so enable stealth mode and a proxy in the session options on the extract job, and allow a generous polling window because these jobs can take a minute or two per site. If one site fails to extract, carry on with the others and note the failure in the digest rather than aborting the whole run.

Filter the extracted reviews down to those published since the last successful run, and keep a high water mark of the most recent review date already processed so nothing gets counted twice. On the very first run, treat reviews from the last 24 hours as new.

Read the new reviews and group them into themes, where a theme is one underlying issue or request that may show up across several reviews and several sites. Classify each theme as a bug, a feature request, or praise.

For every bug or feature request theme, first run Linear Search Issues using the theme's key terms to check whether we already track it. Judge whether a result is genuinely the same underlying problem rather than just a keyword match. If it already exists, use Add Comment to Issue to append the new customer quote, the star rating, the review site, and the review date. If nothing matches, use Create Issue with the theme as the title and a description holding a short summary plus the supporting quotes with their ratings and sources. Any theme whose reviews are three stars or below should be set to high priority. Praise themes do not get a Linear issue, they only appear in the digest.

Finish with a single Slack Send a Message digest to our product channel containing: the number of new reviews, the average star rating across them, the top themes with one representative customer quote each, and links to every Linear issue that was created or updated, clearly labelled as created or updated.

If no new reviews landed since the previous run, skip the Slack post entirely. Do not post a message saying there was nothing to report, just end the run quietly.

## How to customize

- Change the timing. Every weekday at 8am is just a starting point, and Monday only or all seven days works the same way.
- Add or remove review pages. Any public review listing you can link to can be watched, including app store and marketplace pages.
- Move the line for what counts as urgent. Three stars and below is the default for high priority.
- Point praise somewhere else, like a sales or customer success channel, so the product channel stays focused on bugs and requests.

## Example output

New reviews: 7   |   Average rating: 3.4 stars

Top themes

1. Slow CSV export (bug, 3 reviews, avg 2.3 stars)
"Exporting 5,000 rows takes almost four minutes and times out about half the time." 2 stars, G2
GI-482 updated

2. Wants a Xero integration (feature request, 2 reviews, avg 4.0 stars)
"Love the product, but we still rekey every invoice into Xero by hand." 4 stars, Capterra
GI-517 created

3. Onboarding is painless (praise, 2 reviews, avg 5.0 stars)
"Had our whole team live in under an hour without talking to a single salesperson." 5 stars, Trustpilot

Issues created: GI-517
Issues updated: GI-482

## FAQ

### Will it create a duplicate issue every time customers mention the same problem?

No. Before filing anything it searches the issues you already have in Linear, and if the theme is already tracked it adds the new quote and star rating as a comment on that issue instead. You get one issue per problem with the evidence stacking up underneath it.

### What happens on days when nobody leaves a review?

Nothing at all. The digest is skipped entirely rather than posting a message saying there was nothing to report, so the channel only lights up when there is something worth reading.

### Which review sites does this work with?

Any public review page you can link to. G2, Capterra, and Trustpilot are the usual three, and app store or marketplace listings work the same way. You keep the list of pages, so you can add a site whenever you start collecting reviews somewhere new.

### Does it file an issue for positive reviews too?

No. Praise still shows up in the Slack digest so the team sees what customers love, but only bugs and feature requests become Linear issues. That keeps your issue tracker to actual work.

### How does it decide what is urgent?

Star rating. Any theme coming from reviews of three stars or below is created as high priority, on the basis that an unhappy reviewer in public is worth looking at sooner. You can move that line wherever you want.

Use this prompt in General Input: https://www.generalinput.com/prompts/turn-new-customer-reviews-into-linear-issues-every-morning