Detect pipeline stall risk with HubSpot, Slack, OpenRouter and Anthropic
Ready for 3.0What this workflow does
This AI workflow has 38 nodes and runs on a schedule (every week at 06:00) (plus 1 other trigger). Along the way it connects HubSpot, OpenRouter Chat Model, Slack and Guardrails and 1 more.
How it runs
Trigger: On a schedule (every week at 06:00) (plus 1 other trigger).
- Fetch Open Deals (HubSpot) (HubSpot): get many (deal)
- Respond 202 Accepted (Respond to Webhook): sends the response back to the webhook caller
- Normalize Deal Data (Code): runs custom JavaScript code
- Calculate Stall Risk Score (Code): runs custom JavaScript code
- Is Risk High Enough to Analyze (If): checks a condition and branches into true / false
- LLM: Generate Stall Diagnosis (Basic LLM Chain): sends a prompt to an LLM, with model: OpenRouter Chat Model; output parser: Stall Diagnosis Output Parser
- Log: Low/Medium Risk (Code): runs custom JavaScript code
- Parse and Validate LLM Output (Code): runs custom JavaScript code
- Handle LLM Generate Failure (Code): runs custom JavaScript code
- LLM: Audit Diagnosis (Basic LLM Chain): sends a prompt to an LLM, with model: OpenRouter Chat Model; output parser: Auditor Verdict Output Parser
…plus 21 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 (14)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Webhook
n8n-nodes-base.webhook - Respond to Webhook
n8n-nodes-base.respondToWebhook - HubSpot
n8n-nodes-base.hubspot - Code
n8n-nodes-base.code - If
n8n-nodes-base.if - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Slack
n8n-nodes-base.slack - HTTP Request
n8n-nodes-base.httpRequest - Merge
n8n-nodes-base.merge - Guardrails
@n8n/n8n-nodes-langchain.guardrails - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic
From the author
Quick Overview This workflow monitors sales deals from HubSpot or a CRM-agnostic webhook, scores stall risk using deterministic rules, and uses OpenRouter (Anthropic models) plus an Anthropic guardrails check to generate, verify, and safely send Slack alerts…