> ## Documentation Index
> Fetch the complete documentation index at: https://deepline.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Parallel: Decisions

> Answer up to 100 true/false, multiple-choice, or score questions about one company, website, or person in a single cheap web-grounded call, for tagging.

Answer up to 100 true/false, multiple-choice, or score questions about one company, website, or person in a single cheap web-grounded call, for tagging.

> [!NOTE]
>
> Tool ID: `parallel_decisions`

## Run this action

This action has conditional or dynamic inputs. A static example cannot describe these inputs reliably.

Read the live contract before you execute this action:

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
deepline describe parallel_decisions --json
```

## Example response

The SDK returns this shape at `result.toolResponse.raw`. The example values illustrate the response.

```json theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
{
  "data": {
    "mode": "example",
    "answers": {},
    "citations": [
      {
        "url": "https://example.com",
        "excerpts": [
          "example"
        ]
      }
    ],
    "decision_id": "decision_123"
  }
}
```

Use `deepline describe parallel_decisions --json` for the latest machine-readable contract.

## Input reference

Parallel Decisions input. Requires state and questions.

| Name | Type | Required | Default | Details |
| - | - | - | - | - |
| `payload.state` | `unknown` | Yes | — | Required. Context shared by all questions, such as \{"company":"Clay","website":"[https://www.clay.com"\&#125](https://www.clay.com"\&#125);. Any JSON value. |
| `payload.questions` | `record` | Yes | — | Required. 1 to 100 questions keyed by name (ASCII letters, numbers, \_ and -). Answers come back under the same names. |
| `payload.mode` | `"fast"` | No | — | — |
| `payload.advanced_settings` | `object` | No | — | Omit when unused. An empty object is rejected. |

<details>
  <summary>Show raw input schema</summary>

  ### Input JSON Schema

  ```json theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
  {
    "type": "object",
    "description": "Parallel Decisions input. Requires state and questions.",
    "properties": {
      "state": {
        "description": "Required. Context shared by all questions, such as {\"company\":\"Clay\",\"website\":\"https://www.clay.com\"}. Any JSON value."
      },
      "questions": {
        "type": "object",
        "description": "Required. 1 to 100 questions keyed by name (ASCII letters, numbers, _ and -). Answers come back under the same names.",
        "minProperties": 1,
        "maxProperties": 100,
        "additionalProperties": {
          "anyOf": [
            {
              "type": "object",
              "description": "True/false predicate. Answer is the probability (0 to 1) that it is true.",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "noul"
                },
                "instructions": {
                  "type": "string",
                  "minLength": 1
                },
                "criteria": {
                  "type": "object",
                  "properties": {
                    "true": {
                      "type": "string"
                    },
                    "false": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "true",
                    "false"
                  ],
                  "additionalProperties": false
                }
              },
              "required": [
                "type",
                "instructions"
              ],
              "additionalProperties": false
            },
            {
              "type": "object",
              "description": "Pick one named option.",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "choice"
                },
                "instructions": {
                  "type": "string",
                  "minLength": 1
                },
                "criteria": {
                  "type": "object",
                  "description": "2 to 255 options: option name -> when it applies. Add an \"unknown\" option when insufficient evidence must be explicit.",
                  "additionalProperties": {
                    "type": "string"
                  }
                }
              },
              "required": [
                "type",
                "instructions",
                "criteria"
              ],
              "additionalProperties": false
            },
            {
              "type": "object",
              "description": "Rate against ordered levels. Answer is the probability-weighted mean level index.",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "score"
                },
                "instructions": {
                  "type": "string",
                  "minLength": 1
                },
                "criteria": {
                  "type": "array",
                  "description": "Ordered levels, lowest first (2 to 10).",
                  "minItems": 2,
                  "maxItems": 10,
                  "items": {
                    "type": "string"
                  }
                }
              },
              "required": [
                "type",
                "instructions",
                "criteria"
              ],
              "additionalProperties": false
            }
          ]
        }
      },
      "mode": {
        "type": "string",
        "const": "fast"
      },
      "advanced_settings": {
        "type": "object",
        "description": "Omit when unused; an empty object is rejected.",
        "properties": {
          "location": {
            "type": "string",
            "description": "ISO 3166-1 alpha-2 country code, e.g. us or gb."
          },
          "after_date": {
            "type": "string",
            "description": "Prefer sources published on or after YYYY-MM-DD."
          },
          "include_excerpts": {
            "type": "boolean",
            "default": true
          }
        },
        "additionalProperties": false
      }
    },
    "required": [
      "state",
      "questions"
    ],
    "additionalProperties": false
  }
  ```
</details>

## Output reference

Parallel Decisions result payload.

| Name | Type | Required | Default | Details |
| - | - | - | - | - |
| `result.data` | `object` | Yes | — | Provider response payload. |
| `result.data.mode` | `string` | Yes | — | — |
| `result.data.answers` | `record` | Yes | — | — |
| `result.data.citations` | `array` | Yes | — | — |
| `result.data.citations[].url` | `string` | Yes | — | — |
| `result.data.citations[].title` | `string \| null` | No | — | — |
| `result.data.citations[].excerpts` | `array` | Yes | — | — |
| `result.data.decision_id` | `string` | Yes | — | — |
| `result.meta` | `record` | No | — | Additional response metadata (status, paging). |

<details>
  <summary>Show raw output schema</summary>

  ### Output JSON Schema

  ```json theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
  {
    "type": "object",
    "description": "Parallel Decisions result payload.",
    "properties": {
      "data": {
        "type": "object",
        "description": "Provider response payload.",
        "properties": {
          "mode": {
            "type": "string"
          },
          "answers": {
            "type": "object",
            "additionalProperties": {
              "type": "object",
              "description": "Answer keyed by question name. type \"refusal\" carries no value; handle it as its own outcome.",
              "properties": {
                "type": {
                  "type": "string",
                  "enum": [
                    "noul",
                    "choice",
                    "score",
                    "refusal"
                  ]
                },
                "noul": {
                  "type": "number"
                },
                "choice": {
                  "type": "string"
                },
                "score": {
                  "type": "number"
                },
                "legend": {
                  "type": "object",
                  "additionalProperties": {
                    "type": "string"
                  }
                },
                "probabilities": {
                  "type": "object",
                  "additionalProperties": {
                    "type": "number"
                  }
                },
                "confidence": {
                  "type": [
                    "number",
                    "null"
                  ]
                }
              },
              "required": [
                "type"
              ],
              "additionalProperties": false
            }
          },
          "citations": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "url": {
                  "type": "string"
                },
                "title": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "excerpts": {
                  "type": "array",
                  "items": {
                    "type": "string"
                  }
                }
              },
              "required": [
                "url",
                "excerpts"
              ],
              "additionalProperties": false
            }
          },
          "decision_id": {
            "type": "string"
          }
        },
        "required": [
          "mode",
          "answers",
          "citations",
          "decision_id"
        ],
        "additionalProperties": false
      },
      "meta": {
        "type": "object",
        "description": "Additional response metadata (status, paging).",
        "additionalProperties": {}
      }
    },
    "required": [
      "data"
    ],
    "additionalProperties": false
  }
  ```
</details>

## Deepline cost

* Pricing model: `fixed` (per call).
* Estimated Deepline credits: `0.02` per pricing unit.

## Related documentation

* [Connect integrations](https://deepline.com/docs/integrations.md)
* [SDK V2 quickstart](https://deepline.com/docs/sdk-v2/quickstart.md)
* [SDK reference](https://deepline.com/docs/sdk-v2/sdk-reference.md)
* [Run tools across a CSV](https://deepline.com/docs/sdk-v2/batch-csv.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.