Review GitLab merge requests with parallel Azure OpenAI reviewers
Ready for 3.0What this workflow does
This AI workflow has 35 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Azure OpenAI Chat Model.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Workflow Configuration (Edit Fields (Set)): sets 6 fields: gitlabBaseUrl, reviewTriggerPhrase, minConfidenceToPost…
- Check Review Trigger Comment (If): checks a condition and branches into true / false
- Fetch Merge Request Changes (HTTP Request): calls an HTTP API
- Post Review Started Reply (HTTP Request): calls an HTTP API (POST)
- Split Changed Files (Split Out): splits a list into separate items
- Filter Supported Diffs (If): checks a condition and branches into true / false
- Prepare Review Context (Code): runs custom JavaScript code
- Analyze Security Risks (AI Agent): runs an AI agent, with model: Security Reviewer Model; output parser: Parse Security Review Output
- Analyze Bugs (AI Agent): runs an AI agent, with model: Bug Reviewer Model; output parser: Parse Bug Review Output
- Analyze Maintainability Risks (AI Agent): runs an AI agent, with model: Maintainability Reviewer Model; output parser: Parse Maintainability Review Output
…plus 16 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- Webhook
n8n-nodes-base.webhook - If
n8n-nodes-base.if - HTTP Request
n8n-nodes-base.httpRequest - Split Out
n8n-nodes-base.splitOut - Code
n8n-nodes-base.code - Merge
n8n-nodes-base.merge - AI Agent
@n8n/n8n-nodes-langchain.agent - Azure OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatAzureOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Edit Fields (Set)
n8n-nodes-base.set
From the author
Who this template is for This template is for teams that use GitLab merge requests and want a practical AI-assisted review workflow in n8n. It is useful for engineering teams that want faster first-pass reviews, consistent review comments, and a simple way to…