Investigate CI/CD incidents in Slack with a GPT-5.5 AI agent
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 13 nodes and runs when another workflow calls it. Along the way it connects MCP Client, OpenAI Chat Model and Slack.
How it runs
Trigger: When another workflow calls it.
- Call 'attachmentsAnalyzer' (Execute Sub-workflow): calls another n8n workflow
- Merge: merges the data from its input branches
- Set: empty attachments (Edit Fields (Set)): sets 2 fields: attachments_context, attachments_count
- SetVars (Edit Fields (Set)): sets 13 fields: GITLAB_GROUP, LOKI_UID, K8S_NAMESPACE…
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 5 tools (k8s, Slack, Gitlab, Grafana…)
- Send a message (Slack): uses Slack
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 (9)
- Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - MCP Client Tool
@n8n/n8n-nodes-langchain.mcpClientTool - Edit Fields (Set)
n8n-nodes-base.set - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Slack
n8n-nodes-base.slack - Merge
n8n-nodes-base.merge - Execute Sub-workflow
n8n-nodes-base.executeWorkflow
From the author
Overview It is a sub-workflow that investigates CI/CD failures reported by engineers in Slack. It is invoked by a parent classifier and it runs an autonomous AI Agent that diagnoses the failing pipeline, job, or deployment without making any changes.…