Automation library · Chat assistants

Compare A/B AI image edits with CNAPS MCP and Claude

Started by someone submitting a form, and works across Slack. It hands the judgement calls to Claude. 13 steps, 1 branch, 1 loop or waits: a working afternoon to understand properly.

MediumCalls a model: Claude

13 stepsMedium: a working afternoon
1Branch: places the flow splits
1Loop or waits
1Service it connects to

The flow

Starts it 1Model 4Logic 6Service 2

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

  1. 1On form submissionForm triggerStarts it
  2. 2Anthropic Chat ModelLm Chat AnthropicModel
  3. 3CNAPS MCPMcp Client ToolModel
  4. 4SettingsSetLogic
  5. 5Start A/B edit on CNAPSAgentModel
  6. 6Check flow statusAgentModel
  7. 7Wait for the modelsWaitLogic
  8. 8Parse editsCodeLogic
  9. 9Both edits ready?IfLogic
  10. 10Slack, post resultsSlackService
  11. 11Slack, post failureSlackService
  12. 12Merge notificationsMergeLogic
  13. 13Run summaryCodeLogic

How it's built

Starts on
Someone submitting a form
Steps
13, with 1 branch, 1 loop or waits
Size
Medium: a working afternoon
Connects to
Slack
Model
Claude

Questions

What does it need to run?

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

What starts it?

It starts on someone submitting a form.

Does it use AI?

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

How long does it take to set up?

Plan an afternoon. 13 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 13 steps before you point it at anything that matters.