Visual Verification Agent
Pricing
$0.20 / actor start
Visual Verification Agent
An AI-powered Virtual QA Engineer that verifies your website's visual integrity across Desktop, Mobile, and Tablet. Using advanced vision models, it mimics human interaction to detect layout flaws, providing granular 0-100 quality scores and detailed defect analysis from 15+ global locations.
Pricing
$0.20 / actor start
Rating
0.0
(0)
Developer

Techforce
Actor stats
0
Bookmarked
1
Total users
0
Monthly active users
10 days ago
Last modified
Categories
Share
Visual Verification Agent ππ΅οΈββοΈ
This agent acts as a Virtual QA Engineer. It visits your website from different countries, captures high-resolution screenshots across multiple devices (Desktop, Mobile, Tablet), and uses AI (GPT-4o or Gemini) to analyze the visual quality.
It mimics human behavior with natural scrolling to ensure all lazy-loaded content is visible before verifying.
β Features
- Multi-Model Analysis: Choose between OpenAI (GPT-4o) for precision or Google Gemini for cost-efficiency.
- Letter Grading System: Automatically assigns grades (A+, A, B, C) based on visual quality:
- A+ (Excellent): 90-100% Quality. No issues.
- A (Good): 75-89% Quality. Very minor cosmetic issues.
- B (Fair): 60-74% Quality. Noticeable issues but functional.
- C (Fail): <60% Quality. Critical defects or broken layout.
- Human-Like Emulation:
- Natural Scrolling: Smooth, variable-speed scrolling to trigger lazy loaders without "bot-like" jumps.
- Reading Pauses: Mimics real user behavior while reading content.
- Multi-Device Testing: Verifies layout on Desktop (1366x768), Mobile (390x844), and Tablet (768x1024).
- Global Geo-Location: Checks your site from 15+ Major Countries (US, UK, Germany, India, Singapore, Australia, etc.) using stealth geolocation injection.
π How to Use
- Open the Actor on Apify.
- Enter the Target URL.
- Select your AI Provider (Gemini or OpenAI) and enter the API Key.
- Choose the Country you want to test from.
- Select Devices (Desktop, Mobile, Tablet).
- Click Run.
π§© Input Configuration
| Field | Type | Description |
|---|---|---|
url | String | The website to verify (e.g., https://example.com) |
modelProvider | Select | Choose AI Model: gemini or openai |
apiKey | String | Your API Key for the selected provider |
country | Select | Geo-location source (e.g., US, GB, DE, IN, SG, CA, AU...) |
devices | Multiselect | Test environments: desktop, mobile, tablet |
π¦ Output Structure
The actor saves screenshots to the storage/ Key-Value Store and pushes a flattened list of results to the Dataset. Each row verifies one device:
[{"url": "https://example.com","country": "US","device": "desktop","grade": "A+","reason": "Excellent. No visual defects found."},{"url": "https://example.com","country": "US","device": "mobile","grade": "C","reason": "Severe. Hamburger menu overlaps logo."},{"url": "https://example.com","country": "US","device": "tablet","grade": "B","reason": "Average. Needs few modifications for UX."}]
π Support
For issues, questions, or feature requests:
Email: bhavin.shah@techforceglobal.com
Made with β€οΈ for the Data Extraction community
π Book a 15-min consultation
This Actor can be integrated into a fully automated n8n workflow no manual steps, just end-to-end automation.


