Triage network read and commit requests via Slack with Anthropic and pyATS
Needs changesWhat this workflow does
This AI workflow has 56 nodes and runs on Slack events (plus 1 other trigger). Along the way it connects Slack, Postgres, MCP Client and Anthropic Chat Model.
How it runs
Trigger: On Slack events (plus 1 other trigger).
- Lookup Slack Requester (Slack): work with user
- Webhook Response Handler (Respond to Webhook): sends the response back to the webhook caller
- Create Standby Message Pool (Code): runs custom JavaScript code
- Analyze Slack Card Action (Code): runs custom JavaScript code
- Post Standby Message to Slack (Slack): uses Slack
- Lookup Commit Proposal from Commit Ledger (Postgres): run a query
- Extract Slack Mention by Bot (Code): runs custom JavaScript code
- Merge Slack Action and Stored Proposal (Code): runs custom JavaScript code
- Strategic Planning AI Agent (AI Agent): runs an AI agent, with model: Your Planning LLM; 1 tool (Read-only pyATS MCP Client); memory: Planning Memory Buffer; output parser: Structured Output Parser
- Verify Decision Approval (If): checks a condition and branches into true / false
…plus 28 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- Item Lists (legacy) in Expand Commit Cards List: replace with Split Out, Aggregate, Sort, Limit, Remove Duplicates or Summarize (match the operation used).
- Also check Slack Trigger requires a signing secret on the Slack API credential.
| Removed in 3.0 | Replace with |
|---|---|
| Item Lists (legacy) Expand Commit Cards List | Split Out, Aggregate, Sort, Limit, Remove Duplicates or Summarize (match the operation used) |
Nodes used (16)
- If
n8n-nodes-base.if - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Item Lists
n8n-nodes-base.itemLists - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Slack
n8n-nodes-base.slack - AI Agent
@n8n/n8n-nodes-langchain.agent - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Postgres
n8n-nodes-base.postgres - Webhook
n8n-nodes-base.webhook - MCP Client Tool
@n8n/n8n-nodes-langchain.mcpClientTool - Respond to Webhook
n8n-nodes-base.respondToWebhook - Slack Trigger
n8n-nodes-base.slackTrigger - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic
From the author
Quick overview AI-powered Slack ChatOps for data networks housekeeping. Uses AI agents, a ledger DB and Cisco pyATS MCP server to perform on-demand device checks and validations, generate config change proposals, require human approval before committing, and…