OutSend

Catalog of outsend data modules: what each one needs and produces. Call this first to know what is possible. Modules listed as coming_soon cannot be launched.

{
  "type": "object",
  "properties": {}
}

Machine contract for building pipelines: valid block types, per-block config schema, and chaining rules. Use before create_pipeline.

{
  "type": "object",
  "properties": {}
}

Estimate the cost (EF) and volume of a Google Maps extraction WITHOUT launching it. Always estimate before creating a large job. 1 EF = a full-France scrape for one query type.

{
  "type": "object",
  "properties": {
    "queries": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 20,
      "description": "Business types, e.g. ['plombier', 'electricien']"
    },
    "zones": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 50,
      "description": "Cities, departments, regions or 'France'"
    },
    "country": {
      "type": "string",
      "description": "ISO3 country code, default FRA"
    },
    "stop_at": {
      "type": "integer",
      "minimum": 1,
      "description": "Stop after N unique places (recommended when the user gives a number)"
    },
    "scrap_mode": {
      "type": "string",
      "enum": [
        "fast",
        "normal",
        "ultra"
      ]
    }
  },
  "required": [
    "queries",
    "zones"
  ]
}

Launch a Google Maps extraction (async). Returns the job id immediately; poll get_job until status=done, then use get_job_results. When the user wants ~N results, set stop_at.

{
  "type": "object",
  "properties": {
    "queries": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 20
    },
    "zones": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 50
    },
    "country": {
      "type": "string",
      "description": "ISO3, default FRA"
    },
    "stop_at": {
      "type": "integer",
      "minimum": 1
    },
    "scrap_mode": {
      "type": "string",
      "enum": [
        "fast",
        "normal",
        "ultra"
      ]
    },
    "extra_columns": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "gps",
          "departement",
          "region"
        ]
      }
    },
    "max_per_phone": {
      "type": "integer",
      "minimum": 0
    }
  },
  "required": [
    "queries",
    "zones"
  ]
}

Enrich the results of a finished job (async): find emails, scrape reviews, detect social networks, verify emails, tech stack, etc. Returns the new job id.

{
  "type": "object",
  "properties": {
    "enrichment": {
      "type": "string",
      "enum": [
        "ads_intelligence",
        "brand_assets",
        "dead_check",
        "emails",
        "legal_data",
        "legal_ids",
        "legal_mentions",
        "pagespeed",
        "phone_info",
        "phones_extra",
        "pricing",
        "reviews",
        "socials",
        "techstack",
        "verify_emails"
      ]
    },
    "source_job_id": {
      "type": "string",
      "description": "A job with status=done"
    },
    "email_mode": {
      "type": "string",
      "enum": [
        "normal",
        "deep"
      ],
      "description": "Only for enrichment=emails. Default normal."
    }
  },
  "required": [
    "enrichment",
    "source_job_id"
  ]
}

Status, counters and download URL of a job.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ]
}

Preview of a finished job's rows (max 50 per call, paginate with offset) + total count + CSV download URL. Never dump thousands of rows into the conversation: show a sample, give the link.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0
    }
  },
  "required": [
    "job_id"
  ]
}

The account's recent jobs, newest first.

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  }
}

Create AND start a multi-step pipeline (e.g. scrap → emails → verify_emails). Keep chains LINEAR (each block feeds the next). Edges use the keys "from" and "to" — NOT source/target. Call get_pipeline_schema first for the valid block types and their config fields. Returns pipeline id + initial job ids. Example definition: {"nodes": [{"id": "n1", "type": "scrap", "config": {"queries": ["plombier"], "zones": ["Lyon"], "stop_at": 500}}, {"id": "n2", "type": "emails", "config": {}}], "edges": [{"id": "e1", "from": "n1", "to": "n2"}]}

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 100
    },
    "definition": {
      "type": "object",
      "description": "{nodes: [{id, type, config}], edges: [{id, from, to}]} — edge keys are \"from\"/\"to\", not source/target",
      "properties": {
        "nodes": {
          "type": "array",
          "items": {
            "type": "object"
          }
        },
        "edges": {
          "type": "array",
          "items": {
            "type": "object"
          }
        }
      },
      "required": [
        "nodes"
      ]
    }
  },
  "required": [
    "definition"
  ]
}

The account's pipelines with status.

{
  "type": "object",
  "properties": {}
}

Turn a finished job or pipeline into recurring monitoring: outsend re-runs it every N days and computes the diff (new / removed / modified places).

{
  "type": "object",
  "properties": {
    "source_job_id": {
      "type": "string"
    },
    "source_pipeline_id": {
      "type": "string"
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100
    },
    "frequency_days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 90
    }
  },
  "required": [
    "name",
    "frequency_days"
  ]
}

The account's recurring monitors.

{
  "type": "object",
  "properties": {}
}

Account event feed (job.completed, pipeline.completed, veille.run_completed…). Cursor-based: pass back last_id as since_id.

{
  "type": "object",
  "properties": {
    "since_id": {
      "type": "integer",
      "minimum": 0
    },
    "types": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    }
  }
}