[ Fe Forge ]
Sign In
Automated Design Thinking

Forge your
designplan for how people truly behave.

Not how they say they do.

15 years of design audits turned into a tool. Forge scans URLs, screenshots, and mockups across five cognitive layers and tells you what converts and what doesn't. Scored analysis, specific prescriptions, round-over-round convergence. No vibes. Measurement.

See How It Works
forge converge 
Round 3 of 4 · Score: 71 → est. 88

Reasoning
  .hero-cta competes with nav for first-fixation.
  User's eye path splits. Trust decision delays.
  L1 violation: two equal-weight targets in 50ms window.

Fixed this round
  ✓ CTA contrast raised, nav weight reduced     L1
  ✓ spacing rhythm in .feature-grid             L2
  ✓ font-size ramp on mobile nav                L2

Still open
  → .price-tag color distance too low            3.8:1
  → .cart-summary whitespace crowded             L2

$ forge converge --continue
55 Research Citations
5 Perception Layers
15 Years Applied
Cognitive Science Foundation

How it works

Each mode fits a different moment in your design process.

search

Scan

Submit a URL, screenshot, mockup, or code file. Get scored analysis across all five layers with specific findings and prescriptions.

forum

Consult

Ask any design question. The AI reasons layer-by-layer through PFD, produces comparison tables, and references prior scans from the same session.

auto_awesome

Synthesize

Bring in research, prior scans, and project context. Forge cross-references everything and produces optimized plans with prescriptions already applied.

Built for your workflow

Run it where you already work

Forge is an API. Call it from Claude, ChatGPT, any MCP-compatible client, or your own CLI scripts. Perception-First Design™ analysis without leaving your workflow.

Claude Code MCP Server REST API CLI
claude 
$ forge analyze ./src/components/ --type directory

Scanning 14 files across 3 directories...

Cognitive Load  92  Cognitive load within limits
L1          64  50ms visual judgment splitting
L2          38  Spacing + color rhythm broken
L3          72  Anchoring and framing adequate
L4          88  Conversion path clear

Score: 47/100  · Round 1 of 4
Priority: L2 Processing Fluency
→ Generating prescriptions...
→ Applying fixes to plan.md
→ Re-scanning for Round 2...

The 5 Layers

Perception-First Design™ diagnostic framework

Five layers of human perception, scored individually. Fix the lowest layer first. Everything above it depends on the foundation below.

L0

Cognitive Load

Health
92%
L1

First Impression

Health
64%
L2

Processing Fluency

Health
38%
L3

Perception Bias

Health
72%
L4

Decision Architecture

Health
88%
Initial Audit
42

Before Forge

Critical: High Friction Visual Noise Low Contrast Hidden Nav

"Users failed to identify the primary CTA within the first 3 seconds of exposure during attention mapping."

Post-Optimization
89

After 4 Rounds

Resolved: Optimized Flow Focal Alignment WCAG AAA Compliance

"The hierarchy guides without friction. Users see the CTA first, trust the page fast, and follow the path you designed."

arrow_forward

Investment

Choose your diagnostic level

Solo
$0 / mo
  • check $1/week API budget
  • check URL & screenshot scanning
  • check Scored across all 5 layers
  • check Resets every Monday
Recommended
Professional
$39 / mo
  • check $5/week API budget
  • check Every input type — URLs, images, code, copy, directories
  • check Round-over-round scoring with fix tracking
  • check AI design consultation
  • check API & MCP integration
  • check Full exportable reports
Coming Soon
Agency
$129 / mo
  • check $15/week API budget
  • check Everything in Professional
  • check Branded report generator — your logo, your colors
  • check Competitive benchmarking — scan & compare
  • check Historical score tracking over time
  • check Separate client workspaces
  • check Team seats & collaboration
  • check Priority processing
Coming Soon
See all 5 perception layers

Most design feedback is opinion.
This is measurement.

Five perception layers. Specific prescriptions. Round-over-round convergence tracking. Grounded in cognitive science, not vibes.

55 citations · 15 years applied · Cognitive science foundation