Share via


Cradl AI (Preview)

OCR, extract, and review structured information from PDFs, images, handwriting, and scans. Build your own purpose-built AI agent to automate your document workflow.

This connector is available in the following products and regions:

Service Class Regions
Copilot Studio Premium All Power Automate regions except the following:
     -   US Government (GCC)
     -   US Government (GCC High)
     -   China Cloud operated by 21Vianet
     -   US Department of Defense (DoD)
Logic Apps Standard All Logic Apps regions except the following:
     -   Azure Government regions
     -   Azure China regions
     -   US Department of Defense (DoD)
Power Apps Premium All Power Apps regions except the following:
     -   US Government (GCC)
     -   US Government (GCC High)
     -   China Cloud operated by 21Vianet
     -   US Department of Defense (DoD)
Power Automate Premium All Power Automate regions except the following:
     -   US Government (GCC)
     -   US Government (GCC High)
     -   China Cloud operated by 21Vianet
     -   US Department of Defense (DoD)
Contact
Name Cradl AI Support
URL https://www.cradl.ai
Email support@cradl.ai
Connector Metadata
Publisher Cradl AI
Website https://www.cradl.ai
Privacy Policy https://docs.cradl.ai/legal/privacy-policy
Categories AI;Content and Files

Cradl AI

Cradl AI empowers organizations to automate any document workflow with purpose-built AI agents. Fast, flexible and zero code.

🚀️ Create customized AI Agents for any document type in any Latin-based language.
👍 Deploy a fully fledged human-in-the-loop validation UI with one click
🎉️ Automatically improve your Agent based on feedback from end users.

Publisher: Cradl AI

Prerequisites

A free Cradl AI account. If you don't already have one, you can sign up for free here.

Supported Operations

This connector supports the following operations:

Extract Data From Document

Extract data from documents like invoices, receipts, order confirmations.

Extracted Data From Document

Trigger that runs when data is extracted from a document.

Validate Trigger Output

Validate output from trigger, to make sure that the output originates from Cradl.

Get Document

Get the content of a document.

Get Document Metadata

Get metadata like name and content-type from a document.

Create Document (deprecated)

Create a new document.

Parse Document with Human-in-the-Loop (deprecated)

Parse a document with Flows. This operation runs asynchronous.

Parse Document (deprecated)

Parse a document by calling the model directly. This operation runs synchronously.

Obtaining Credentials

Log into Cradl AI, and in your Agent select either a Power Automate trigger or export and copy Credentials to the Client Credentials field.

Getting Started

This quick start guide aims to provide a basic overview how Cradl AI can be integrated in a Power Automate Flow. Please refer to the official documentation for up-to-date documentation.

1. Set up an Agent

Cradl AI Agents enables you to automate internal document processes in a simple, effective and unified way. It reduces the risk of using AI Agents in production since you can send uncertain documents to a human-in-the-loop when necessary. By adjusting confidence thresholds of your agent, you can decide when a document should be sent to manual verification and when it's allowed to pass straight through.

2. Configure a Power Automate Trigger

Navigate to your Cradl AI Agent, in the Trigger section, select Power Automate from the list of available integrations. Create a new Flow in Power Automate, and select the action "Extract Data from Document" from Cradl AI. Open the dropdown menu for the parameter Agent and choose the Agent you just modified in Cradl AI. Make sure you have a Trigger in your Power Automate Flow that has a valid file as output.

3. Configure a Power Automate Export

navigate to your Cradl AI Agent, in the Export section, select Power Automate from the list of available integrations. Create a new Flow in Power Automate, and select the trigger "Extracted Data from Document" from Cradl AI. Open the dropdown menu for the parameter Export Action and choose the Action you just created in Cradl AI.

Known Issues and Limitations

See API Limits.

Frequently Asked Questions

Which document formats are supported?

JPEG, PNG, PDF, WEBP and TIFF.

How many Agents do I need?

One per document process. For example, if you want to automate an expense approval process where you process receipts, invoices and airline tickets, we recommend using one Agent even if you process multiple document types with different layouts.

Where is my data stored?

Please refer to our to our Data Processing Agreement and Privacy Policy for more information about how personal data is processed.

Deployment Instructions

Refer the documentation here to deploy this connector as a custom connector in Microsoft Power Automate and Power Apps.

Creating a connection

The connector supports the following authentication types:

Default Parameters for creating connection. All regions Not shareable

Default

Applicable: All regions

Parameters for creating connection.

This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.

Name Type Description Required
Client Credentials securestring Your client credentials. True

Throttling Limits

Name Calls Renewal Period
API calls per connection 100 60 seconds

Actions

Create Document (deprecated)

Create a document.

Extract Data From Document

Extract data from documents like invoices, receipts, order confirmations.

Get Document

Get the content of the Document.

Get Document Metadata

Get metadata like name and content-type from a document.

Parse Document (deprecated)

Extract data from documents like invoices, receipts, order confirmations.

Parse Document With Human-in-the-Loop (deprecated)

Extract data from documents like invoices, receipts, order confirmations.

Validate Trigger Output

Validate output from trigger.

Create Document (deprecated)

Create a document.

Parameters

Name Key Required Type Description
Name
Name True string

The name of your document.

File content
File content True binary

The file content.

Returns

Name Path Type Description
documentId
documentId string

The document ID

Extract Data From Document

Extract data from documents like invoices, receipts, order confirmations.

Parameters

Name Key Required Type Description
Agent
AgentId True string

Choose your agent.

Variables
variables string

json-encoded key-value pairs, e.g. {"origin": "PowerAutomate"}

Title
title string

Title of the document or run.

Document
document True binary

Binary content of the file.

Returns

Name Path Type Description
AgentRunId
runId string

A unique ID for this run

Status
status string

A status indicator for this run

Get Document

Get the content of the Document.

Parameters

Name Key Required Type Description
Document Id
documentId True string

Id of the document, on the form las:document:xxx.

Returns

response
binary

Get Document Metadata

Get metadata like name and content-type from a document.

Parameters

Name Key Required Type Description
Document Id
documentId True string

Id of the document, on the form las:document:xxx.

Returns

Name Path Type Description
DocumentId
documentId string

The document which was parsed

Document Name
name string

The name of the Document

Content Type
contentType string

Content Type of the Document

Parse Document (deprecated)

Extract data from documents like invoices, receipts, order confirmations.

Parameters

Name Key Required Type Description
Model
modelId True string

Choose your model.

Document ID
documentId True string

Name of the file, e.g. Document.pdf.

Output format
outputFormat string

Output format.

The strategy used for aggregating predictions.
strategy string

Prediction aggregation strategy.

autoRotate
autoRotate boolean

A flag indicating whether document orientation should be auto detected

maxPages
maxPages integer

The maximum number of pages to process in a single request

imageQuality
imageQuality string

The image quality used when processing this document

Returns

Name Path Type Description
documentId
documentId string

The document which was parsed

inferenceTime
inferenceTime float

The number of seconds used to process this document

modelId
modelId string

The model which was used

Postprocessing
postprocessConfig PostprocessConfig
Preprocessing
preprocessConfig PreprocessConfig
predictions
predictions object

predictions

trainingId
trainingId string

The model training

Parse Document With Human-in-the-Loop (deprecated)

Extract data from documents like invoices, receipts, order confirmations.

Parameters

Name Key Required Type Description
Workflow
WorkflowId True string

Choose your workflow.

Document ID
documentId True string

The ID of the document which was submitted.

Title
title string

Title, e.g. Invoice.pdf.

Predictions
predictions object

Manually override the predictions used in this workflow execution.

Returns

Name Path Type Description
executionId
executionId string

A unique ID for this execution.

status
status string

A status indicator for this execution.

Validate Trigger Output

Validate output from trigger.

Parameters

Name Key Required Type Description
ActionId
ActionId True string

Id of the Trigger Action (cradl:action:xxx).

X-Cradl-Shared-Secret
X-Cradl-Shared-Secret True string

@{triggerOutputs()['headers']['X-Cradl-Shared-Secret']}

Returns

Triggers

Extracted Data From Document

This operation triggers when data is extracted from your document.

Extracted Data From Document

This operation triggers when data is extracted from your document.

Parameters

Name Key Required Type Description
Export Action
ActionId True string

Id of the action that defines the export.

Returns

The outputs of this operation are dynamic.

Definitions

PostprocessConfig

Name Path Type Description
Output format
outputFormat string

Output format.

The strategy used for aggregating predictions.
strategy string

Prediction aggregation strategy.

PreprocessConfig

Name Path Type Description
autoRotate
autoRotate boolean

A flag indicating whether document orientation should be auto detected

maxPages
maxPages integer

The maximum number of pages to process in a single request

imageQuality
imageQuality string

The image quality used when processing this document

binary

This is the basic data type 'binary'.