Quick overview
This workflow receives app store reviews via a webhook, uses Anthropic Claude to classify and deduplicate technical complaints, checks your bug tracker for an existing issue, then either updates the matched bug or creates a new ticket, posts an alert to Slack, and logs the outcome to a tracking API.
How it works
- Receives a new app store review via a POST webhook and normalizes key fields like rating, text, platform, version, and reviewer handle.
- Uses Anthropic Claude to classify whether the review is a genuine technical complaint, assign an app area and severity, and generate a normalized issue summary.
- Filters out non-technical reviews, marks them as log-only, and skips ticket creation.
- For technical complaints, calls a complaint-search API to fetch similar recent issues and uses Anthropic Claude to decide whether the review matches an existing complaint cluster.
- Searches your bug tracker (via HTTP API) for an existing open issue that matches the complaint and selects the best match above a confidence threshold.
- If a match is found, updates the existing bug with the review as evidence and the reassessed severity; otherwise it creates a new engineering ticket in the bug tracker.
- Sends a Slack message to the routed engineering channel with the issue summary, severity, and review details, then logs the final outcome to a tracking-log API.
Setup
- Configure the review source to send POST requests to this workflow’s webhook URL (path:
/app-store-review-received) and include fields like reviewText, rating, platform, appVersion, and reviewUrl.
- Add an Anthropic credential and select a Claude chat model for the two AI agent steps.
- Set up HTTP header authentication credentials for the complaint-search API, bug-tracker search/update/create endpoints, and the tracking-log API, then update the base URLs in the configuration values.
- Add Slack credentials, ensure the target channels exist, and adjust the app-area-to-team/channel routing map and default channel as needed.