hitlintermediate15 min setupby Mantle

Extract with human clarification on low confidence

Extract structured data from text; when the model is unsure it pauses and asks a person to pick from candidates, then the record is posted.

Use this template See it run with us

React Flow

Drag to pan, pinch to zoom. This is the real graph the template installs.

How it works

What it does

Webhook extract-in → Extract (pause if unsure): on_ambiguity: pause with confidence_threshold: 0.75. When the model's self-reported confidence is low, or it returns several candidates, the run pauses and a person picks the right one in the run panel.
Post order line sends the (possibly human-corrected) fields.

Setup

AI connection on the extractor; adjust the schema, threshold and destination url.

Nodes 3

01Text intrigger.webhookTrigger
02Extract (pause if unsure)ai.extractAI
03Post order linehttp.requestHTTP

View template JSON

{
  "format": "mantle-workflow/v1",
  "id": "hitl-extract-with-clarification",
  "name": "Extract with human clarification on low confidence",
  "graph": {
    "nodes": [
      {
        "id": "webhook",
        "type": "trigger.webhook",
        "label": "Text in",
        "config": {
          "slug": "extract-in",
          "input_schema": {
            "required": [
              "text"
            ],
            "properties": {
              "text": {
                "type": "string"
              }
            }
          }
        },
        "connection_id": null,
        "worker_type": "generic-worker",
        "position": {
          "x": 60,
          "y": 220
        }
      },
      {
        "id": "ai_extract",
        "type": "ai.extract",
        "label": "Extract (pause if unsure)",
        "config": {
          "model": "claude-sonnet-4-5",
          "temperature": 0,
          "text": "{{ $json.text }}",
          "schema": {
            "type": "object",
            "required": [
              "product",
              "quantity"
            ],
            "properties": {
              "product": {
                "type": "string"
              },
              "quantity": {
                "type": "number"
              },
              "confidence": {
                "type": "number",
                "minimum": 0,
                "maximum": 1
              },
              "candidates": {
                "type": "array",
                "items": {
                  "type": "object",
                  "properties": {
                    "label": {
                      "type": "string"
                    }
                  }
                }
              }
            }
          },
          "on_ambiguity": "pause",
          "confidence_threshold": 0.75,
          "confidence_path": "confidence",
          "candidates_path": "candidates",
          "candidate_label_field": "label",
          "ambiguity_question": "Which product did the customer mean?",
          "timeout_seconds": 86400
        },
        "connection_id": null,
        "worker_type": "ai-worker",
        "position": {
          "x": 380,
          "y": 220
        }
      },
      {
        "id": "post_order",
        "type": "http.request",
        "label": "Post order line",
        "config": {
          "method": "POST",
          "url": "https://example.com/order-lines",
          "headers": {
            "Content-Type": "application/json"
          },
          "json": {
            "product": "steps.ai_extract.response.product",
            "quantity": "steps.ai_extract.response.quantity"
          }
        },
        "connection_id": null,
        "worker_type": "generic-worker",
        "position": {
          "x": 700,
          "y": 220
        }
      }
    ],
    "edges": [
      {
        "from": "webhook",
        "to": "ai_extract"
      },
      {
        "from": "ai_extract",
        "to": "post_order"
      }
    ]
  }
}

Use it, then make it yours.

Templates install as drafts. Change anything, and Workflow Health re-checks the graph on every save.

Start free Book a demo