Evidence row 124871

What was observed

{
  "endpoints": [
    [
      "x402",
      "https://x402-agent-tools.nerolabs.workers.dev/ai/enrich"
    ]
  ],
  "name": "Nero Labs Agent Tools",
  "owner_address": "0xa969a3127dcc74b2989a4b4e45ae61b81093164a",
  "raw": {
    "accepts": [
      {
        "amount": "2000",
        "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
        "extra": {
          "name": "USD Coin",
          "version": "2"
        },
        "maxTimeoutSeconds": 300,
        "network": "eip155:8453",
        "payTo": "0xA969a3127DcC74B2989a4b4e45Ae61B81093164A",
        "scheme": "exact"
      }
    ],
    "description": "Applies one plain-English AI instruction to every row of a JSON list (up to 50 rows), such as classify, extract, summarise or score, with {{field}} placeholders, and returns the new columns you define in outputFields for each row. Uses Claude Haiku. $0.002 per row. Runs nerolabs/dataset-ai-enrich.",
    "extensions": {
      "bazaar": {
        "info": {
          "input": {
            "body": {
              "data": [
                {
                  "id": 1,
                  "review": "Battery life is fantastic but the case feels cheap."
                }
              ],
              "outputFields": [
                {
                  "description": "positive, neutral or negative",
                  "name": "sentiment",
                  "type": "string"
                }
              ],
              "prompt": "Classify the sentiment of this review: {{review}}"
            },
            "bodyType": "json",
            "method": "POST",
            "type": "http"
          },
          "output": {
            "example": {
              "_example_note": "Real output, trimmed: long lists cut to their first items, fields and text shortened.",
              "count": 1,
              "rows": [
                {
                  "aiError": null,
                  "aiModel": "anthropic/claude-haiku-4.5",
                  "id": 1,
                  "review": "Battery life is fantastic but the case feels cheap.",
                  "sentiment": "neutral"
                }
              ]
            },
            "type": "json"
          }
        },
        "schema": {
          "$schema": "https://json-schema.org/draft/2020-12/schema",
          "properties": {
            "input": {
              "additionalProperties": false,
              "properties": {
                "body": {
                  "additionalProperties": false,
                  "properties": {
                    "data": {
                      "description": "A JSON array of records to enrich, for ad-hoc data instead of a dataset ID or file URL.",
                      "type": "array"
                    },
                    "includeOriginalFields": {
                      "default": true,
                      "description": "On (default): each output row is the original row plus the new columns. Off: only the new columns (plus aiModel/aiError).",
                      "type": "boolean"
                    },
                    "outputFields": {
                      "description": "The new columns the model must fill in for every row, as a JSON list of {\"name\", \"type\", \"description\"}. Types: string (default), number, boolean, array, object. The description tells the model exactly what goes in the column (allowed values, units, language). Leave empty to get one free-text column",
                      "type": "array"
                    },
                    "prompt": {
                      "description": "Plain-English instruction applied to each row on its own. Use {{field}} placeholders to insert that row's values (dotted paths like {{address.city}} work). Only the fields you reference are sent to the model; if you reference none, every field is sent. Examples: classify, extract a value, score 1 to",
                      "type": "string"
                    },
                    "skipIfEmpty": {
                      "default": true,
                      "description": "On (default): a row with nothing in any {{field}} the instruction uses is written out with 'aiSkipped: true' and never sent to the model or charged.",
                      "type": "boolean"
                    },
                    "systemPrompt": {
                      "description": "Optional background the model should know for every row: your industry, the categories you use, the language to answer in, edge-case rules.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "data",
                    "prompt"
                  ],
                  "type": "object"
                },
                "bodyType": {
                  "enum": [
                    "json",
                    "form-data",
                    "text"
                  ],
                  "type": "string"
                },
                "method": {
                  "enum": [
                    "POST"
                  ],
                  "type": "string"
                },
                "type": {
                  "const": "http",
                  "type": "string"
                }
              },
              "required": [
                "type",
                "method",
                "bodyType",
                "body"
              ],
              "type": "object"
            },
            "output": {
              "properties": {
                "example": {
                  "properties": {
                    "_example_note": {
                      "type": "string"
                    },
                    "count": {
                      "type": "number"
                    },
                    "rows": {
                      "items": {
                        "properties": {
                          "aiError": {},
                          "aiModel": {
                            "type": "string"
                          },
                          "id": {
                            "type": "number"
                          },
                          "review": {
                            "type": "string"
                          },
                          "sentiment": {
                            "type": "string"
                          }
                        },
                        "type": "object"
                      },
                      "type": "array"
                    }
                  },
                  "type": "object"
                },
                "type": {
                  "type": "string"
                }
              },
              "required": [
                "type"
              ],
              "type": "object"
            }
          },
          "required": [
            "input"
          ],
          "type": "object"
        }
      }
    },
    "iconUrl": "https://res.cloudinary.com/bdb-prod/image/upload/c_fill,ar_1:1,w_256,h_256,f_auto,q_auto/v1792616069/bazaar-icons/0a5b056fde952fc0.png",
    "lastUpdated": "2026-10-25T12:54:19.891Z",
    "quality": {
      "l30DaysTotalCalls": 4,
      "l30DaysUniquePayers": 3,
      "lastCalledAt": "2026-10-25T12:54:19.391Z"
    },
    "resource": "https://x402-agent-tools.nerolabs.workers.dev/ai/enrich",
    "serviceName": "Nero Labs Agent Tools",
    "tags": [
      "ai",
      "llm",
      "classify",
      "enrichment",
      "bulk"
    ],
    "type": "http",
    "x402Version": 2
  },
  "source": "x402_bazaar",
  "summary": "Applies one plain-English AI instruction to every row of a JSON list (up to 50 rows), such as classify, extract, summarise or score, with {{field}} placeholders, and returns the new columns you define in outputFields for each row. Uses Claude Haiku. $0.002 per row. Runs nerolabs/dataset-ai-enrich."
}

What the leaf hashes

{"body":"57cef17825ec3835018e32e6e710634e7e6bf3fc9d1419ce85ab38c016f8ec59","id":124871,"kind":"listing","method":"baseline/1","observed_us":1793025625372043,"prev":null,"subject":"x402_bazaar:https://x402-agent-tools.nerolabs.workers.dev/ai/enrich","subject_kind":"source_record"}

Proof

Its day has not closed yet. A day closes ten minutes after midnight UTC; the proof appears here then.