Thursday, October 29, 2026

Feng-GUI Multi-Channel Visual Pre-Testing

Explore everyday visual tasks, persistent performance bottlenecks, and how Feng-GUI’s platform replaces guesswork with empirical attention data.

Websites, Landing Pages & Email Marketing


Above-the-Fold Visual Hierarchy

Task: Structuring above-the-fold content and email hero banners to deliver the value proposition in 3–5 seconds.

Challenge: High bounce rates; rapid visitor scanning causes exits when headlines or hero graphics fail to register, while team debates default to subjective internal opinions rather than empirical data.

How Feng-GUI Resolves It:

  • Heatmap & Focus Map (Opacity) Reports: The Heatmap visualizes the intensity of initial viewer attention, while the Focus Map dims non-engaging areas with an opacity overlay to reveal exactly what users perceive versus what they ignore.
  • Aesthetics Report (Clarity & Complexity Scores): Quantifies visual clutter and compositional cleanliness, providing an objective mathematical benchmark instead of subjective opinions.
  • AI Assistant & Recommendations: Generates automated design critiques and actionable tips to refine visual hierarchy before publishing.

Call-to-Action (CTA) Visibility & Contrast

Task: Positioning and styling primary conversion buttons across forms, landing pages, and email templates.

Challenge: CTA blindness; conversion buttons blend into photography or sit outside the eye’s natural scanning trajectory, depressing conversion rates.

How Feng-GUI Resolves It:

  • Areas of Interest (AOI) & Auto-AOIs: Define manual or automatic AOIs around the CTA button to calculate the exact percentage of attention and fixation scores it commands relative to the rest of the page.
  • Gaze Plot Report (Fixations & Saccades): Maps the chronological sequence of eye fixations (1, 2, 3...) to confirm whether the visitor's gaze path actually reaches the button or gets intercepted by competing graphics.

Pre-Launch Wireframe & Mockup Screening

Task: Evaluating multiple page layouts, form positions, and email variations before committing to code or live media spend.

Challenge: Traditional live A/B testing takes weeks to reach statistical significance and burns expensive traffic on underperforming designs.

How Feng-GUI Resolves It:

  • Compare Reports Feature: Directly compares two or more wireframes or mockup variations side-by-side to evaluate differences in attention flow and overall score.
  • Website Capture Tool & Batch Upload: Allows teams to upload multiple visual variants simultaneously or capture live URLs to assess design iterations in seconds.



Scroll-Stopping Hook Execution

Task: Creating visual hooks for fast-paced feeds across social platforms and programmatic display networks.

Challenge: Sub-500ms scroll speeds; if an ad fails to capture visual interest instantly, the impression is wasted and Customer Acquisition Cost (CAC) rises.

How Feng-GUI Resolves It:

  • Custom View Duration: Configure the analysis to simulate short glance durations (e.g., 0-2.5 second) to see what survives rapid feed scrolling.
  • Auto-AOI Face & Skin Detection: Automatically identifies and measures attention drawn to human faces or models, verifying whether a human hook is anchoring the viewer's gaze.
  • Memory Heatmap (Aesthetics Report): Predicts visual memorability, ensuring the hook is not only noticed in the feed but also retained in memory.

Brand Attribution & Recall

Task: Placing brand logos, pack shots, and product watermarks across display and social creatives.

Challenge: Attribution failure; users engage with an aesthetic photo or model but fail to notice the logo, leading to high spend with zero brand equity built.

How Feng-GUI Resolves It:

  • Logo & Brand AOI Scoring: Set dedicated AOIs over brand marks and product shots to confirm they capture adequate visual share and a high percentage of total fixations.
  • Focus Map Verification: Confirms whether brand assets remain clear and illuminated on the Focus Map or fade into the suppressed, ignored background.

Rapid Creative Variation Auditing

Task: Producing and screening 10–50 creative iterations per campaign (testing different colors, copy overlays, and asset placements).

Challenge: Teams lack fast, data-backed ways to identify winning creatives before allocating ad spend.

How Feng-GUI Resolves It:

  • Overall Score (Visibility + Focus + Clarity): Aggregates algorithmic measurements into an Overall Score (combining Visibility, Focus, and Clarity) for instant ranking of creative variations.
  • Platform API: Seamlessly automates pre-testing by feeding hundreds of programmatic or dynamic creative variations into the backend to filter top performers before ad upload.


eCommerce & Digital Shelf


Primary Hero Image & Search Grid Standout

Task: Designing mobile-ready lead pack shots that stand out in crowded marketplace search grids.

Challenge: Products compete side-by-side against dozens of rivals; packs that blend into the visual grid are scrolled past without clicks.

How Feng-GUI Resolves It:

  • Simulated Shelf & Multi-Product AOI Grid: Upload search result grid mockups and define AOIs around your product versus competitor listings to measure your relative share of attention.
  • Heatmap Intensity Scoring: Highlights hotspot intensity, demonstrating if your hero product acts as the primary visual magnet in search results.

Mobile Thumbnail Legibility & Variant Distinction

Task: Designing packaging and thumbnails so shoppers instantly distinguish sizes, flavors, and key claims on small screens.

Challenge: Small screen thumbnail compression obscures fine print and badges, leading to confusion and lost sales.

How Feng-GUI Resolves It:

  • Custom View Distance Setting: Simulates viewing conditions from a greater visual distance, replicating how human eyes process downscaled mobile thumbnails.
  • Auto-AOI Text Detection: Verifies whether callouts, pack counts, and flavor labels maintain sufficient text saliency and readability at reduced scales.

Task: Designing supporting product detail page carousel images (infographics, feature callouts, lifestyle shots) to answer purchase objections.

Challenge: Visual clutter and disorganized information density cause shoppers to abandon the product gallery.

How Feng-GUI Resolves It:

  • Visual Complexity & Focus Scores: Evaluates whether infographic slides are overloaded or properly balanced for easy visual processing.
  • Gaze Sequence Tracking: Checks the Gaze Plot to ensure eyes follow a clean path from feature callout to benefit icon to proof point.


Packaging & Product Design


Retail Shelf Breakthrough

Task: Creating packaging that breaks through visual noise on supermarket shelves and digital displays.

Challenge: Physical eye-tracking labs are slow, expensive, and logistically burdensome during early concept phases.

How Feng-GUI Resolves It:

  • Heatmap & Saliency Modeling: Upload digital shelf planograms to simulate consumer attention in seconds, identifying whether a prototype pops on the shelf.
  • Compare Reports: Compare previous packaging versions against new prototypes side-by-side to ensure the new design outperforms the legacy design.

On-Pack Claim Hierarchy

Task: Structuring label architecture so shoppers absorb Brand, Flavor/Variant, and Key Claims in the proper order.

Challenge: Cluttered label surfaces overwhelm consumers, causing them to miss key product differentiators within a 2-second decision window.

How Feng-GUI Resolves It:

  • Gaze Plot (Saccades & Fixations): Quantifies the exact order of fixations to confirm consumers read elements in the intended hierarchy.
  • AOI Fixation Share: Establishes AOIs around critical nutritional claims or certifications to confirm they receive adequate visual priority.

Rebrand & Redesign De-Risking

Task: Modernizing packaging while retaining recognizable visual brand assets for loyal buyers.

Challenge: Radical redesigns risk alienating loyal customers if distinctive brand assets (colors, shapes, icons) lose visual dominance.

How Feng-GUI Resolves It:

  • Memory Heatmap & Aesthetics Report: Evaluates whether distinctive shapes and graphic equities remain high-retention visual anchors.
  • Clarity & Balanced Scores: Ensures that decluttering initiatives maintain overall visual balance and do not accidentally weaken the brand's visibility.


Out-of-Home (OOH), Signage & Retail Point of Sale (POS)


Brief-Exposure Legibility (Billboards & Transit)

Task: Designing billboards, transit posters, and roadside displays for motorists and pedestrians on the move.

Challenge: Viewers have roughly 1.5 to 2 seconds to absorb a message; printed and mounted media cannot be easily changed or A/B tested post-install.

How Feng-GUI Resolves It:

  • Custom View Distance & Duration: Adjust settings to simulate roadside viewing distances and brief 0-2.5 second exposure windows.
  • Focus Map & Visibility Score: Reveals what remains legible at a glance and assigns a predictive Visibility Score to confirm the headline and brand register immediately.

In-Store POP/POS Display Differentiation

Task: Designing shelf-talkers, endcaps, and standees that draw shoppers' eyes down crowded retail aisles.

Challenge: Store lighting, visual aisle noise, and competing displays wash out promotional signage.

How Feng-GUI Resolves It:

  • Contextual Environment Simulation: Superimpose POS displays onto photos of real-world store aisles and run Heatmap and Focus Map analyses to verify whether the POP unit pulls visual focus from ambient store clutter.
  • AI Assistant Insights: Provides suggestions to improve contrast, color saturation, and typography hierarchy to maximize physical aisle breakthrough.


Video & Motion Advertising


The First 3-Second Hook Retention

Task: Designing the opening frames of short-form video (Reels, TikTok, Shorts) to stop the user from swiping.

Challenge: If the first few frames lack an immediate focal anchor, viewers swipe away immediately.

How Feng-GUI Resolves It:

  • Video Attention Analysis (Frame-by-Frame): Upload video files to analyze early keyframes, pinpointing the exact trajectory of viewer gaze as motion begins.
  • Face Detection & Emotional Saliency: Automatically identifies human faces and emotional expressions in opening frames to verify high-engagement emotional hooks.

Brand Attribution Before the Skip

Task: Placing branding, product cues, and value propositions within non-skippable windows (e.g., YouTube pre-roll before the 5-second skip).

Challenge: Viewers skip the ad at the 5-second mark, resulting in zero brand attribution if the logo or product is delayed or placed outside focal attention.

How Feng-GUI Resolves It:

  • Merged Video Overall Scores: Overlays attention and clarity scores onto bottom video timelines to pinpoint exactly where engagement dips.
  • Milestone Static AOI Analysis: Export individual high-impact video frames directly into image analysis to measure exact brand Area of Interest (AOI) attention percentages at crucial moments of exposure.

Interface Safe-Zone Alignment

Task: Positioning dynamic CTAs, captions, and text overlays away from native social platform interfaces.

Challenge: Native UI elements (like comment buttons, share icons, and account handles) often cover vital text, causing readability friction.

How Feng-GUI Resolves It:

  • Focus Map & Gaze Plot Overlays: Run keyframe audits with UI safe-zone guides applied to verify that viewer fixations land cleanly on your CTA and captions without competing with interface elements.
  • Clarity Score: Ensures text overlays are uncluttered and readable against moving backgrounds throughout the video's progression.

Tuesday, September 08, 2026

Connecting your AI Assistant to Feng-GUI MCP Server


Connecting your AI Assistant to Feng-GUI MCP Server

You can now connect your favorite AI assistants (like Claude, Cursor, or custom AI agents) directly to Feng-GUI using the Model Context Protocol (MCP). Once connected, your AI can automatically run visual attention analytics on images and videos directly within your chat.


To connect your AI, you will need your Feng-GUI API Key, which can be found in your account settings.

For Claude Desktop Users (No coding required)

If you are using the Claude Desktop app, you can easily connect it to Feng-GUI by editing your configuration file.

Open your Claude Desktop configuration file:

Windows: %APPDATA%\Claude\claude_desktop_config.json
Mac: ~/Library/Application Support/Claude/claude_desktop_config.json

Add the Feng-GUI server to your mcpServers list exactly like this (making sure to replace YOUR_API_KEY with your actual key):

{
   "mcpServers": {
   "FengGUI": {
   "type": "sse",
   "url": "https://mcp.feng-gui.com/sse",
   "headers": {   "x-api-key": "YOUR_API_KEY"}
  }
 }
}


Restart Claude Desktop. You will now see the Feng-GUI tools available in your chat!
Just ask Claude: "Use Feng-GUI to analyze this image URL..."

For Cursor IDE Users

If you are using Cursor, you can add Feng-GUI directly through the settings interface:

Go to Cursor Settings > Features > MCP.
Click + Add New MCP Server.
Name: FengGUI
Type: sse
URL: https://mcp.feng-gui.com/sse

Click the settings/headers icon next to the URL and add:
Key: x-api-key
Value: <your-api-key>

For Developers & Custom AI Agents

If you are building your own AI agents (using frameworks like LangChain, LlamaIndex, or custom scripts), Feng-GUI provides a fully hosted, standard MCP Server via Server-Sent Events (SSE).

Configure your MCP Client with the following connection details:
  • Transport Protocol: SSE (Server-Sent Events)
  • SSE Endpoint: https://mcp.feng-gui.com/sse
  • Authentication: Pass your API key via the x-api-key HTTP Header.

Once the SSE connection is established, your MCP client will automatically discover all available tools (like ImageAttention and VideoAttention) and their required JSON schemas. The gateway strictly handles routing and execution, translating your agent's intents into standard Feng-GUI API calls.

You may also find the API Documentation at https://feng-gui.com/api

How to talk to the AI

Once connected, your AI knows exactly how to use Feng-GUI. You can simply prompt it in plain English:
  • Run an ImageAttention analysis on https://example.com/ad.jpg and summarize the hotspots.
  • What are the most complex areas of this design according to Feng-GUI?
  • Use Feng-GUI to check if the logo in this image gets enough attention.

Saturday, August 22, 2026

Optimize & Redesign CTAs with Feng-GUI AI

Getting users to take action on your website starts with a simple reality: if they don’t notice your Call-to-Action (CTA), they won’t click it.

Traditionally, finding out whether a button stands out required waiting weeks for live A/B testing or setting up costly eye-tracking studies. With Feng-GUI’s predictive attention algorithms and built-in AI Assistant, you can now evaluate visual prominence, receive data-backed optimization tips, and generate a redesigned mockup—all in just a few minutes.

Here is a quick look at the end-to-end workflow covered in our latest video tutorial.

1. Baseline Analysis & Auto AOIs

Start by selecting your webpage screenshot from your project gallery. Using Create Auto AOIs, Feng-GUI automatically identifies key elements across your layout—including buttons, headlines, and visuals—giving you instant metrics like Visibility Score and Time to First Fixation (TTFF).


2. Get Strategic Guidance from the AI Assistant

If a primary button (like cta-3) shows low visibility or takes too long to attract attention, simply open the AI Assistant and ask:

"How can I improve the Visibility score and Time to first fixation of cta-3?"

The assistant analyzes visual contrast, surrounding whitespace, and layout hierarchy to provide concrete design recommendations.


3. Generate a Redesigned Mockup on the Spot

Instead of switching back and forth between design software, you can ask the AI Assistant:

"Use the above recommendations to create a new website design image."

Within seconds, the AI outputs a freshly generated visual design incorporating higher contrast, optimized placement, and cleaner visual flow.


4. Validate the Results with the Compare Report

To measure the impact, copy your original AOIs onto the newly generated design and run the analysis. Using the Compare Report, you can review the before-and-after versions side-by-side to verify higher visibility scores and faster visual engagement before pushing changes live.


Why It Matters

Eliminate Guesswork: Base your design iterations on simulated human visual attention rather than subjective opinions.

Accelerate Prototyping: Move seamlessly from diagnostic data to AI-generated mockups in a single platform.

Maximize Conversions: Ensure your most critical conversion elements get noticed within the first critical seconds of page load.

🎬 Watch the Full Tutorial

Ready to see this workflow in action? Watch the step-by-step video above, or log in to feng-gui.com to test and optimize your own designs today!


Sunday, August 16, 2026

New: WebP, HEIC & Expanded Video Uploads


Great visual analysis should be effortless, and that starts the moment you upload your creatives.

We know how frustrating it is to stop your workflow just to convert an iPhone photo or re-export a video file. That’s why we’ve expanded Feng-GUI’s upload capabilities to support 6 new modern image and video formats:

  • Next-Gen Images: WebP and HEIC

  • Expanded Video Formats: WebM, MOV, MKV, and AVI


What This Means for Your Workflow

  • Zero Conversion Hassle: Drop photos straight from your iPhone or iPad (HEIC) without converting them to JPEG first.

  • Modern Web Ready: Test lightweight web-optimized assets (WebP and WebM) directly from your design or web tools.

  • Direct Video Exports: Analyze commercials, UI animations, and video ads straight out of Premiere, Final Cut, or After Effects using MOV, AVI, or MKV formats alongside standard MP4s.

  • Faster Turnarounds: Save valuable minutes on every project, keep your creative momentum going, and get instant visual attention heatmaps in fewer clicks.

Whether you're testing mobile-shot packaging, high-res digital signage, or interactive web creatives, Feng-GUI now adapts to your files - not the other way around.

Ready to see what catches your audience’s eye?
Log in to your dashboard and drag-and-drop your latest assets today!

Wednesday, July 08, 2026

Quirk's Marketing Research Media - 20 AI Tool Providers

 We’re thrilled to be included in Quirk's Marketing Research Media’s list of the Top 20 AI Tool Providers, recognizing the innovators shaping the next generation of market research.


Tuesday, June 23, 2026

Visual Insights for AI: The Feng-GUI MCP Server



Visual Insights for AI: The Feng-GUI MCP Server

Digital agencies and research agencies are constantly looking for ways to back their creative strategies with objective data. While AI assistants have made generating and refining ideas faster, they often lack a structured way to evaluate how humans actually perceive visual media. 

To bridge this gap, we are excited to launch the Feng-GUI MCP Server in beta. By wrapping the Feng-GUI API into a Model Context Protocol (MCP) server, we are making it possible for your AI agents to access visual insights natively within their workflows.

Bring Visual Analysis into AI Workflows

The Model Context Protocol (MCP) allows AI models, such as Claude, to connect securely and dynamically with external APIs. For agencies and research teams, this means your AI workflows can now call upon Feng-GUI directly to:

  • Predict attention: See where users are most likely to focus within the first few seconds of viewing an asset.
  • Analyze emotional responses: Gain a deeper understanding of how visual elements might emotionally resonate with viewers.
  • Measure memorability: Evaluate which parts of an image, campaign, or interface are most likely to be remembered.

Your AI assistants can then process these visual insights in real-time to suggest precise, data-driven improvements to layouts, advertisements, or packaging designs.

Empowering Designers with Smarter Iteration

UX, UI, and graphic designers can also benefit immensely from this integration. Instead of relying on manual testing cycles, designers can ask their AI assistants to evaluate layouts, review attention scores, and suggest actionable adjustments. This helps ensure that key visual elements, such as Call-to-Action (CTA) buttons or brand logos, stand out as intended before a single mock-up is finalized.

Access Details and Setup

The Feng-GUI MCP server is currently in beta. To utilize this integration, you must be a registered Feng-GUI customer with the 'api' role enabled on your account. 

If you meet these requirements, you can get started by connecting to the MCP server via Server-Sent Events (SSE) at: https://mcp.feng-gui.com/sse

Feng-GUI API documentation https://docs.api.feng-gui.com

We invite agencies, researchers, and designers to explore this integration and bring empirical visual insights to their daily AI workflows.

Saturday, June 06, 2026

Updated DPA, Sub-processors, and AI Terms

At Feng-GUI, we know that as AI becomes a larger part of your daily workflow, data privacy and compliance are more important than ever. Whether you are a small agency or a Fortune 500 brand, you need total peace of mind when uploading unreleased designs and ad campaigns.

To meet strict enterprise standards and global privacy regulations (like GDPR and the upcoming EU AI Act), we have officially published our Data Processing Agreement (DPA) and completely updated our AI Terms.

Here is a simple summary of our new updates:

New DPA & Sub-processor Transparency
We have published a formal Data Processing Agreement (DPA). This legal document outlines exactly how we handle and protect your data. Alongside it, we have listed our approved sub-processors, the secure, third-party infrastructure services we use to run Feng-GUI. You now have 100% transparency into where and how your data is processed.

No AI Model Training
We have made our legal language crystal clear: we explicitly guarantee that your private inputs and outputs are never used to train, test, or fine-tune our core AI models or any third-party models. Your data belongs only to you.

Your Data is Isolated (Logical Separation)
We added explicit guarantees that your data is completely isolated. Your inputs (like images) and outputs (like heatmaps) are kept strictly separate from other customers, third-party providers, and our own internal data. We never mix your proprietary designs into a shared "data lake."

Enterprise Compliance (Auditable Logs)
To support the strict compliance requirements of our enterprise clients, we now formally maintain secure audit logs of AI feature usage. If your company's IT or legal team ever needs to verify what data went into the AI and what came out for an internal audit, we have the records ready for you.

How Our Predictive AI Works
We added a few standard industry clarifications about how predictive AI operates. Because our AI predicts human attention, if two users upload similar designs, the AI may generate similar insights. We also included a quick reminder that while our platform provides highly accurate mathematical predictions of human behavior, they are still predictions!

What this means for you
These updates do not change how you use Feng-GUI or affect your pricing. They simply provide you and your legal teams with the concrete, contractual guarantees needed to use our tools safely and confidently.

You can review the full updated agreements here:

DPA & Sub-processors: https://feng-gui.com/dpa

AI Terms: https://feng-gui.com/ai

As always, if you or your legal team have any questions, feel free to reach out to us!

Wednesday, February 04, 2026

New Aesthetics Report - Memory Heatmap

Introducing the New Aesthetics Report

We’ve redesigned our Aesthetics Report to make it more intuitive and actionable.

The new report (with Memory heatmap) will go live during February 2026.

The old report (with Balance lines) is deprecated and will be obsolete on September 1st 2026.

The previous report focused on vertical and horizontal balance metrics. While technically accurate, these indicators were often hard to interpret and didn’t clearly explain what to change in an image.

The updated report now centers on visual memorability, combining a clear Memory Score with an easy-to-read Memory Heatmap.



The heatmap shows how attention is distributed across the image:

  • Red – Highly noticeable and memorable areas
  • Yellow – Medium memorability
  • Blue – Low memorability

Instead of abstract balance values, the new report shows what viewers actually will remember. This makes it easier to validate focal points, reduce visual competition, and optimize layouts with confidence.

The result is a more human-centered, actionable aesthetic analysis designed to support real creative decisions.

Monday, January 12, 2026

Postman Collection and Examples of Feng-GUI API


Postman Collection
For practical examples of request syntax and hands-on testing, you may find the API documentation and collection available on Postman helpful. 

These resources are commonly used for learning, exploration, and validating API requests alongside this documentation


GET (URL)
In addition to the standard POST syntax, for simplified access or quick testing via a browser, the API also supports requests via the GET method. In this format, the method name is appended to the base URL as a path, and parameters are passed as standard URL query strings.

GET URL Structure:
https://service.feng-gui.com/json/api.ashx/[METHOD]?id=[ID]&[PARAM1]=[VALUE1]&[PARAM2]=[VALUE2]

Example GET Request:
https://service.feng-gui.com/json/api.ashx/ImageAttention?id=1&InputImage=https://service.feng-gui.com/users/USERNAME/files/images/IMAGEID.png&ViewType=0&ViewDistance=0&AnalysisOptions=0&OutputOptions=0

Demo page of GET API methods
FG-JSON-GET-Demo.html


for more, see the main API page at https://feng-gui.com/developers

Tuesday, November 04, 2025

Overall Score - the total visual effectiveness of the entire image

The "Overall Score" is a composite metric that represents the total visual effectiveness of the entire image. It combines multiple attention-based scores - Visibility, Focus, Clarity, and Exciting - 
into a single, easy-to-compare value. 

The score reflects how well the image captures attention, maintains visual focus, and delivers clear and engaging content overall 
The value ranges from 0 to 100. 
  • Above 75 is excellent. The image is highly noticeable and engaging. 
  • Between 50–75 is good. The image attracts a moderate level of attention. 
  • Under 25 is low. The image is not drawing meaningful attention.