Share via

Tiliter Vision Agents (Preview)

Run Tiliter Vision Agents to analyse images and extract insights. Agents can check cleanliness, detect damage, validate labels, count or confirm objects, process receipts, extract text, detect people, identify tyres, analyse fitting rooms, and more.

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 Tiliter Support
URL https://www.tiliter.com
Email support@tiliter.com
Connector Metadata
Publisher Tiliter Pty Ltd
Website https://www.tiliter.com
Privacy policy https://www.tiliter.com/privacy
Categories AI;Productivity

Tiliter Vision Agents Connector

Overview

The Tiliter Vision Agents Connector enables seamless integration with Tiliter’s Vision Agent Platform, allowing automation workflows to interact with AI-powered product recognition and operational intelligence services.

What's New

  • Updated connector structure to support multiple Vision Agents.
  • Added support for handling agent-specific operations within a unified connector.
  • Improved schema alignment for easier use in flows.

Supported Operations

  • Run Vision Agent
  • Validate results
  • Retrieve agent information

Change Log

**Version 2.3.0

  • Restructured connector to handle multiple agents.
  • Added new endpoints and operations.
  • Updated policies and connection parameters accordingly.

Usage Notes

  • Ensure that you create a connection using valid Tiliter Vision Agent API credentials.
  • This connector is certified for use 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
X-API-Key securestring The X-API-Key for this api True

Throttling Limits

Name Calls Renewal Period
API calls per connection 100 60 seconds

Actions

Run Vision Agent

Run any Tiliter Vision Agent on an image (JPEG or PNG). PDF is also supported for text extractor and receipt processor. Some agents require additional input parameters such as expected_text, object_type, or expected_objects.

Run Vision Agent

Operation ID:
runVisionAgent

Run any Tiliter Vision Agent on an image (JPEG or PNG). PDF is also supported for text extractor and receipt processor. Some agents require additional input parameters such as expected_text, object_type, or expected_objects.

Parameters

Name Key Required Type Description
Vision Agent to run
 agent_name True string

Select the Vision Agent you want to run on your image.
Image (Base64 or URL)
 input_file_b64 True string

Base64 encoded string with data URL prefix (e.g. data:image/jpeg;base64,...) or a public image URL.
Expected text (for label-reader-validator)
 expected_text string

Use only with label-reader-validator.
Object type (for object-counter)
 object_type string

Use only with object-counter.
Expected objects (for object-validator)
 expected_objects array of string

Use only with object-validator.

Returns

Body
AgentResponse

Definitions

AgentResponse

Name Path Type Description
success
 success boolean
agent_type
 agent_type string
result
 result object

Agent-specific result fields
agent_id
 metadata.agent_id string
request_id
 metadata.request_id string