Generate PII-Safe Helpdocs from Crisp Support Chats with GPT-4.1-mini
Turn Crisp chats into Helpdocs
Automatically create help articles from resolved Crisp chats. This n8n workflow listens for chat events, formats Q&A pairs, and uses an LLM to generate a PII‑safe helpdoc saved to a Data Table.
Highlights
🧩 Trigger: Crisp Webhook when a chat is marked resolved. 🗂️ Store: Each message saved in a Data Table (crisp). 🧠 Generate: LLM turns Q&A into draft helpdoc. 💾 Save: Draft stored in another Data Table (crisphelp) for review.
How it works
Webhook receives message:send, message:received, and state:resolved events from Crisp. Data Table stores messages by session_id. On state:resolved, workflow fetches the full chat thread. Code node formats messages into Q: and A: pairs. LLM (OpenAI gpt-4.1-mini) creates a redacted helpdoc. Data Table crisphelp saves the generated doc with publish = false.
Requirements
Crisp workspace with webhook access (Settings → Advanced → Webhooks) n8n instance with Data Tables and OpenAI credentials
Customize
Swap the model in the LLM node. Add a Slack or Email node after store-doc to alert reviewers. Extend prompt rules to strengthen PII redaction.
Tips
Ensure Crisp webhook URL is public. Check IF condition: {{$json.body.data.content.namespace}} == "state:resolved". Use the publish flag to control auto‑publishing.
Category: AI • Automation • Customer Support
Related Templates
Use OpenRouter in n8n versions <1.78
What it is: In version 1.78, n8n introduced a dedicated node to use the OpenRouter service, which lets you to use a lot...
Task Deadline Reminders with Google Sheets, ChatGPT, and Gmail
Intro This template is for project managers, team leads, or anyone who wants to automatically remind teammates of tasks ...
🤖 Build Resilient AI Workflows with Automatic GPT and Gemini Failover Chain
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. How it works This...
🔒 Please log in to import templates to n8n and favorite templates
Workflow Visualization
Loading...
Preparing workflow renderer
Comments (0)
Login to post comments