Reply to support emails in-thread with SendRaven and OpenAI
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 18 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects OpenAI Chat Model. It also calls api.sendraven.ai over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Read raw body (Extract from File): extracts data from a file (text)
- Compute expected signature (Crypto): hashes or encrypts values
- Signature valid? (If): checks a condition and branches into true / false
- Acknowledge (200) (Respond to Webhook): sends the response back to the webhook caller
- Reject (401) (Respond to Webhook): sends the response back to the webhook caller
- Skip webhook retries (Remove Duplicates): removes duplicate items
- Inbound email (Edit Fields (Set)): sets or maps fields
- Needs an answer? (If): checks a condition and branches into true / false
- Settings (Edit Fields (Set)): sets 3 fields: company, sign_off, about
- Get thread (HTTP Request): calls an HTTP API
…plus 4 more steps. See the full node list below.
Services it uses
HTTP calls to: api.sendraven.ai
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 (13)
- Webhook
n8n-nodes-base.webhook - Extract from File
n8n-nodes-base.extractFromFile - Crypto
n8n-nodes-base.crypto - If
n8n-nodes-base.if - Respond to Webhook
n8n-nodes-base.respondToWebhook - Remove Duplicates
n8n-nodes-base.removeDuplicates - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Switch
n8n-nodes-base.switch - No Operation, do nothing
n8n-nodes-base.noOp
From the author
Quick Overview This workflow receives inbound support emails from SendRaven via a signed webhook, loads the full email thread, uses an OpenAI-powered agent to decide whether to reply, mark the thread handled, or escalate, and posts any reply back through…