visual-evaluation

Here are 4 public repositories matching this topic...

Can AI agents rebuild websites through browser exploration?

A visual prompt iteration studio for comparing outputs, scoring transformations, and refining prompts with feedback and optional AI assistance.

Modular visual evaluation and computer-vision framework for image QA, structured annotation, reliability analysis, and human pose data.

Evidence-driven visual iteration for agents: owner gates, calibrated critics, max-zoom fidelity, discovery history and domain packs.

To associate your repository with the visual-evaluation topic, visit your repo's landing page and select "manage topics."