Automation library · Chat assistants

Mask PII in hosted chat with OpenAI and Claude

Started by an arriving email, and works across Gmail and Slack. It hands the judgement calls to OpenAI. 6 steps: small enough to read in one sitting and change without fear.

SmallCalls a model: OpenAI

6 stepsSmall: readable in one sitting
0Branches: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 1Model 2Logic 2Service 1

The steps in the order they run, from what starts it.

  1. 1When new support email arrivesGmail triggerStarts it
  2. 2Claude via Saklam BridgeLm Chat Open AiModel
  3. 3⚙️ SettingsSetLogic
  4. 4Summarize & triage (masked)AgentModel
  5. 5🔍 What got maskedCodeLogic
  6. 6Post summary to SlackSlackService

How it's built

Starts on
An arriving email
Steps
6
Size
Small: readable in one sitting
Connects to
Gmail, Slack
Model
OpenAI

Questions

What does it need to run?

An n8n account, plus your own Gmail and Slack accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an arriving email.

Does it use AI?

Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Not long. At 6 steps it can be read in one sitting and changed without fear.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 6 steps before you point it at anything that matters.