Get faster, consistent feedback on merge requests. This setup reads code changes in GitLab and posts clear review notes where they matter. It helps engineering teams reduce review time and keep quality high.

A webhook receives a merge request event. A filter checks if the update should be reviewed based on your trigger words. The flow then calls the GitLab API to get the list of changed files, splits them, and skips files that do not need feedback. Code nodes parse the diff to pull the original code and the new code. An AI prompt builds a focused review using these snippets, and the system posts an inline discussion back to the exact file and line in GitLab.

You need a GitLab project webhook, a GitLab access token, and an OpenAI API key. After setup, teams see faster reviews and fewer back and forth comments. It is a good fit for product teams with steady merge request volume, for onboarding junior developers, and for teams that want consistent comments on style and risky changes.

• Webhook trigger listens for merge request events from GitLab
• Conditional check runs reviews only when event data matches your trigger words
• HTTP request pulls changed files and diffs from the GitLab API
• Split node processes each changed file independently
• If logic skips files that are not relevant to code review
• Code nodes parse the diff to extract original and new code blocks
• Prompt builder crafts a clear AI review message with code context
• OpenAI Chat Model generates concise, actionable suggestions
• HTTP request posts an inline discussion to the correct file and line in GitLab

• Reduce manual review time from 30 minutes to 5 minutes per merge request
• Automate up to 60 percent of repetitive review comments
• Post precise feedback to the exact file and line to avoid confusion
• Support up to three times more merge requests without adding reviewers
• Connect GitLab and OpenAI in one reliable review flow

1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
2. You'll need accounts with GitLab and OpenAI. See the Tools Required section above for links to create accounts with these services.
3. In your OpenAI account, create an API key. In n8n, open the OpenAI node, click the credential dropdown, choose Create new credential, and paste your API key. Save the credential.
4. In GitLab, create a Personal Access Token with API scope. Copy the token and keep it secure.
5. Open the HTTP Request nodes labeled Get Changes and Post Discussions. In the credential dropdown, click Create new credential and add the PRIVATE-TOKEN header using your GitLab token. Save the credential and apply it to both nodes.
6. Open the Webhook node and copy the Production URL. Keep the HTTP method as POST and confirm the path is unique.
7. In your GitLab project settings, add a Webhook that points to the n8n Webhook Production URL. Select Merge request events and save.
8. Edit the Need Review and Skip File Changes If nodes to set your trigger words or file type filters. Use simple text checks to include or exclude events and files.
9. Open the Basic LLM Chain node and adjust the prompt text to match your code standards and tone. Keep the placeholders for original and new code.
10. Click Execute Test on the Webhook node, then trigger a test merge request in GitLab. Confirm the workflow runs and reaches Post Discussions without errors.
11. Check the merge request in GitLab for a new inline discussion. If no comment appears, verify the file path and line values in the Post Discussions node and confirm the token has the correct scope.
12. If you see authentication errors, recheck your GitLab token and OpenAI key. If payload errors occur, ensure your GitLab webhook is sending Merge request events and that the n8n Webhook URL matches the one in GitLab.