Documentation

← All agent examples

Check user images: stock photo, AI-generated or unsuitable?

Scores an image and its accompanying text: how likely the image is a stock photo or AI generated, how well image and text match, and whether it suits all audiences. Low-confidence ratings go to a person for review.

Moderation
Content
moderation
vision
scoring
human in the loop
trust and safety

How it starts

When you run it.

Accepts files: Image

What it needs

No knowledge base, memory bank or connection to create first.

Steps

Rate the image and text

Prompt Call

Parse and validate the scores

Extract Content

Is confidence low?

If / Else

If yes:

Review the rating

Human-in-the-Loop

Otherwise:

Rated without review

Text

Show the rating

Display Result