Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.deck.co/llms.txt

Use this file to discover all available pages before exploring further.

Available on Enterprise plans.
Tasks can produce files like receipts, invoices, statements, reports, images, videos, and spreadsheets. When storage is enabled on a task, Deck captures the files the agent is instructed to collect and makes them available through the API. If extraction is also enabled, Deck parses supported files and returns structured JSON alongside the raw file.

​
Enabling storage on a task

Storage is configured when you create or update a task. Set storage.enabled to true to capture files. Set storage.extraction to true to also extract structured data from those files. 
POST /v2/tasks

{
  "name": "Fetch utility bills",
  "agent_id": "agt_a1b2c3d4...",
  "input_schema": {
    "type": "object",
    "properties": {
      "start_date": { "type": "string" },
      "end_date": { "type": "string" }
    }
  },
  "output_schema": {
    "type": "object",
    "properties": {
      "bill_count": { "type": "integer" }
    }
  },
  "storage": {
    "enabled": true,
    "extraction": true,
    "deduplication": true
  }
}
FieldTypeDescription
storage.enabledbooleanCapture files produced during task execution
storage.extractionbooleanParse captured files and extract structured data
storage.extraction_schemaobjectCustom schema to guide what gets extracted
storage.deduplicationbooleanSkip files that have already been stored from a previous run

​
Retrieving storage items

Storage items are not included in the default task run response. Use ?include=storage to include them when retrieving a task run, or list them separately using the task run storage endpoint. 
curl https://api.deck.co/v2/task-runs/trun_a1b2c3d4/storage \
  -H "Authorization: Bearer sk_live_your_key_here"

{
  "data": [
    {
      "id": "stor_x1y2z3...",
      "object": "storage",
      "file_name": "statement_jan_2025.pdf",
      "file_type": "application/pdf",
      "file_size": 245678,
      "metadata": null,
      "fetch_date": "2025-01-15T09:30:00Z",
      "extraction": null
    },
    {
      "id": "stor_a4b5c6...",
      "object": "storage",
      "file_name": "statement_dec_2024.pdf",
      "file_type": "application/pdf",
      "file_size": 198432,
      "metadata": null,
      "fetch_date": "2025-01-15T09:30:05Z",
      "extraction": {
        "company_name": "EnergyLink",
        "account_number": "58291-44720",
        "billing_date": "2024-12-22",
        "amount_due": 6925.18,
        "currency": "USD"
      }
    }
  ],
  "has_more": false,
  "next_cursor": null,
  "request_id": "req_f5g6h7..."
}

​
Storage item fields

​
id
string
Unique identifier, prefixed with stor_.
​
file_name
string
Original file name as it appeared on the source.
​
file_type
string
MIME type (application/pdf, image/png, video/mp4, text/csv, etc.).
​
file_size
integer
Size in bytes.
​
url
string
Signed download URL.
​
metadata
object
Source-specific metadata attached by Deck during capture.
​
fetch_date
datetime
When the file was retrieved from the source.
​
extraction
object or null
Structured data extracted from the file, if extraction is enabled.
​
task_run_id
string
The task run that produced this storage item.

​
Downloading files

Each storage item includes a url field with a signed download URL. Use it to fetch the raw file. 
curl -O "https://storage.deck.co/stor_x1y2z3..."
Retrieve a single storage item by ID to get a fresh download URL. The single-item response includes additional fields (url, task_run_id, created_at) not present on list items. 
curl https://api.deck.co/v2/storage/stor_x1y2z3 \
  -H "Authorization: Bearer sk_live_your_key_here"

​
Document extraction

When extraction is enabled, Deck parses the captured files and populates the extraction field on each storage item with structured JSON. Extraction works with common document types including PDFs, spreadsheets, invoices, receipts, and reports. The extracted data depends on the document. A utility bill produces different fields than a hotel receipt.

​
Custom extraction schemas

Use the extraction_schema field on the task’s storage config to define exactly what fields you want extracted. Deck uses this schema to guide parsing. 
{
  "storage": {
    "enabled": true,
    "extraction": true,
    "extraction_schema": {
      "type": "object",
      "properties": {
        "vendor_name": { "type": "string" },
        "total_amount": { "type": "number" },
        "invoice_date": { "type": "string", "format": "date" },
        "line_items": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "description": { "type": "string" },
              "amount": { "type": "number" }
            }
          }
        }
      }
    }
  }
}

​
Extraction example

A utility bill extraction might return: 
{
  "company_name": "EnergyLink",
  "account_number": "58291-44720",
  "billing_date": "2025-01-22",
  "billing_period": {
    "start_date": "2024-12-18",
    "end_date": "2025-01-20",
    "total_days": 33
  },
  "amount_due": 8247.41,
  "payment_due_date": "2025-02-14",
  "currency": "USD",
  "service_locations": [
    {
      "service_type": "Fuel",
      "service_address": {
        "street": "4421 OAK VIEW LN UNIT 3A",
        "city": "CAMBRIDGE",
        "state": "MA",
        "postal_code": "02140"
      },
      "total_usage": 5348,
      "total_usage_unit": "Therms",
      "total_charges": 8214.67
    }
  ]
}

​
Extraction errors

If extraction fails on a file, the extraction field is null. The raw file is still available for download. Only the extraction step failed. Common causes:
Error codeMeaning
extraction_failedThe file couldn’t be parsed. Corrupt, unsupported layout, or unreadable content.
extraction_timeoutExtraction took too long

​
Deduplication

Deduplication is off by default. When storage.deduplication is true, Deck compares files against previous runs for the same task and credential. If a file has already been stored, it’s skipped. This is useful for recurring fetch tasks. Run the same task daily and only new files are captured.

​
Events

Storage items emit events you can subscribe to through event destinations:
EventWhen it fires
storage.createdA new file has been captured and is ready for download
storage.deletedA storage item was permanently removed

​
Retention

Retention period varies by plan. All files are deleted after 90 days.