⚙️ Analyze Alertmanager incidents and post diagnostic reports to Mattermost
⚡ 93 views · ⚙️ DevOps & CI/CD
Description
Overview
This workflow helps automatically analyze alerts occurring in the infrastructure and suggest solutions even before the on-duty engineer sees the alert.
How it work
- Workflow receives alert from Alertmanager via Webhook.
- The variables required for operation are set
- Preparing a prompt for the agent containing only the data necessary for analysis
- Optional step to deduplicating duplicate alerts
- Getting the trigger condition
- The agent performs diagnostics as described in the system prompt. During operation, it can access various systems via MCP to obtain additional information.
- Search for a message in a Slack channel corresponding to a processed alert
- Send report to Slack thread.
How to use
- Generate webhook credentials and use it in Alertmanager
- Add Alert fingerprint into Slack message template
- Set variables it SetVars node
- Add your own Rules and recomendations to system promt 5 Run mcp servers
- Choose Slack channel with alerts
🔗 Nodes Used
HTTP Request, Webhook, Mattermost, AI Agent, OpenAI Chat Model, Qdrant Vector Store
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File