Frontend Review FAQs

Question 1

How does Frontend Review integrate with my workflow?

Accepted Answer

It integrates with AI agents via MCP (Micro Code Platform) and can be easily added to Cursor and Windsurf IDEs using provided configuration snippets.

Question 2

What information does Frontend Review need to perform a review?

Accepted Answer

It requires the absolute paths to the 'before' and 'after' screenshots of the UI, along with a detailed description of the UI edit request.

Question 3

What is Frontend Review?

Accepted Answer

Frontend Review is a tool that visually reviews UI edits by comparing before and after screenshots, providing detailed feedback using AI to ensure edits satisfy the request.

Question 4

Which Large Vision Models does Frontend Review use?

Accepted Answer

It primarily uses `Qwen/Qwen2-VL-72B-Instruct` and falls back to other models like `Qwen/Qwen2-VL-7B-Instruct`, `meta-llama/Llama-3.2-90B-Vision-Instruct`, and `mistralai/Pixtral-12B-2409` for robust review processing.

Question 5

How do I configure Frontend Review to use a different review model?

Accepted Answer

You can specify the desired model using the `MODEL` argument in the command line, like this: `npx frontend-review-mcp HYPERBOLIC_API_KEY= MODEL=`.

Frontend Review

主な機能

ユースケース

Frontend Review

主な機能

ユースケース