Use the Workflow Agent (video tutorial)

Last updated: May-10-2026

Overview

Cloudinary's Workflow Agent lets you build complex MediaFlows automations from natural language descriptions. Simply describe your workflow requirements, and the agent will understand your request, align it with your taxonomy and folder structure, and generate a draft flow that you can review, configure, and enable.

In this tutorial, you'll learn how to use the Workflow Agent to create an automated moderation workflow that checks uploaded assets against rules, applies automatic corrections, and routes images based on moderation results.

Video tutorial


This video is brought to you by Cloudinary's video player - embed your own!
Use the controls to set the playback speed, navigate to chapters of interest and select subtitles in your preferred language.

Tutorial contents

This tutorial presents the following topics. Click a timestamp to jump to that part of the video.

Introduction

Jump to this spot in the video  0:00 Cloudinary's Workflow Agent lets you build complex MediaFlows automations from natural language descriptions. Simply describe what you want your workflow to do, and the agent will create it for you.

Describing a workflow

Jump to this spot in the video  0:06 In this example, a workflow is automatically triggered when an asset fails moderation. The workflow checks which rule failed and applies appropriate actions. For a clean white background rule failure, automatic background removal and normalization are applied. Another rule checks if the image was AI-generated or copied from the internet.

Understanding and planning

Jump to this spot in the video  0:25 The agent understands your request, aligns it with your current taxonomy and folder structure, and lays out a detailed plan before building anything.

Building the draft flow

Jump to this spot in the video  0:31 When you give it the go-ahead, the agent automatically builds the draft flow based on your requirements.

Reviewing the flow

Jump to this spot in the video  0:40 Review the generated flow to see the logical layout. In this example, you can see two checks: first for a clean white background, and next for either AI-generated or non-original images, which then routes them appropriately.

Configuring blocks

Jump to this spot in the video  0:55 Go into any block to further configure its settings and fine-tune the workflow behavior.

Testing and enabling

Jump to this spot in the video  1:02 Run a test to troubleshoot and verify the workflow works as expected, then enable the automation to start processing assets automatically.

Keep learning

Related topics

If you like this, you might also like...

 

Cloudinary Academy

 

Check out the Cloudinary Academy for free self-paced Cloudinary courses on a variety of developer or DAM topics, or register for formal instructor-led courses, either virtual or on-site.

 

✔️ Feedback sent!

Rate this page:

one star two stars three stars four stars five stars