Turn new customer reviews into Linear issues every morning

By General Input

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

Integrations

  • Hyperbrowser
  • Linear
  • Slack

Type

Agentic Task

Categories

  • Product
  • Customer Support

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.

Related prompts

Explore more prompts
Call overdue Xero customers with an AI collections agentWin back LiveChat visitors whose chats went unansweredChat quality review board for LiveChat support leadsWin back no-show and cancelled appointments every morningLive Loop returns analytics with product-level drill-downNewsletter pre-flight and approval board for Mailjet sendsTurn a prospect spreadsheet into personalized sequence enrollmentsMailjet email delivery lookup console for support teamsCatch feature flags that never got switched on in productionKajabi customer support console for member access fixes