Mask PII in hosted chat with OpenAI, Claude, and Saklam Bridge
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 6 nodes and runs on Gmail events. Along the way it connects Gmail, OpenAI Chat Model and Slack.
How it runs
Trigger: On Gmail events.
- ⚙️ Settings (Edit Fields (Set)): sets 2 fields: slack_channel, summary_language
- Summarize & triage (masked) (AI Agent): runs an AI agent, with model: Claude via Saklam Bridge
- 🔍 What got masked (Code): runs custom JavaScript code
- Post summary to Slack (Slack): post (message)
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.
- Still check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll) (When new support email arrives).
Nodes used (6)
- Gmail Trigger
n8n-nodes-base.gmailTrigger - Edit Fields (Set)
n8n-nodes-base.set - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Code
n8n-nodes-base.code - Slack
n8n-nodes-base.slack
From the author
Quick overview This workflow provides a public hosted chat that routes messages through the Saklam Bridge to mask PII on-premises before calling models like Claude, GPT, or Mistral, then restores the original values in the response. How it works 1. Exposes a…