Automation library · AI assistants

Redact and restore PII around Claude Sonnet tasks

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to OpenRouter. 9 steps: a working afternoon to understand properly.

MediumCalls a model: OpenRouter

9 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
0Services by connector: it calls them over plain HTTP

The flow

Starts it 1Model 5Logic 3

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

  1. 1Chat TriggerChat triggerStarts it
  2. 2Spans SchemaOutput Parser StructuredModel
  3. 3OpenRouter Chat ModelLm Chat Open RouterModel
  4. 4OpenRouter Chat Model1Lm Chat Open RouterModel
  5. 5Pass 1: Structured PII (regex + checksum)CodeLogic
  6. 6Pass 2: Unstructured PII (LLM)Chain LlmModel
  7. 7Your AI Task (replace me)Chain LlmModel
  8. 8Merge Pass 2 TokensCodeLogic
  9. 9Restore TokensCodeLogic

How it's built

Starts on
Someone opening a chat with it
Steps
9
Size
Medium: a working afternoon
Connects to
Nothing by connector; it calls services over plain HTTP
Model
OpenRouter

Questions

What does it need to run?

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

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

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

How long does it take to set up?

Plan an afternoon. 9 steps is enough that you should read each one before running it.

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 9 steps before you point it at anything that matters.