Automation library · AI assistants

Evaluation metric example: Correctness (judged by AI)

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

MediumCalls a model: OpenAI

Download free
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 2Model 3Logic 2Service 2

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

  1. 1OpenAI Chat ModelLm Chat Open AiModel
  2. 2When fetching a dataset rowEvaluation triggerStarts it
  3. 3When chat message receivedChat triggerStarts it
  4. 4AI AgentAgentModel
  5. 5Match chat formatSetLogic
  6. 6Evaluating?EvaluationService
  7. 7Calculate correctness metricOpen AiModel
  8. 8Return chat responseNo OpLogic
  9. 9Set metricsEvaluationService

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
OpenAI

Questions

What does it need to run?

An n8n account, and a key for OpenAI. 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 OpenAI. 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.