Platform

Two surfaces.
One engine.

A dashboard for product and design teams to track UX quality across releases. An MCP server for developers to get UX feedback inside their IDE before commit. Same engine, same categories, same fix-ready output.

Start free See a live demo

DDashboard· after you ship

The living report that tracks your product.

Not a PDF you download once. A continuous surface that tracks every release, surfaces regressions, and delivers fixes your team can act on today.

The single metric

UX Score at a glance

One number that captures your product's experience quality. Tracks release over release. See what improved, what regressed, what stayed flat.

30%

Behavioral

20%

Visual

20%

A11y

15%

Usability

15%

Cognitive

5 dimensions, 9 core + 2 neurodiversity categories. Weighted composite backed by 200+ peer-reviewed studies.

app.corexi.ai

UX Score

+5 vs last scan

app.corexi.ai

Corexi findings list showing prioritized UX issues with severity

12 findings

3 high · 5 medium · 4 low

Evidence-based

Prioritized findings

Every issue ranked by severity with concrete evidence: contrast ratios, pixel measurements, element counts. No vague recommendations.

Severity-ranked with quantified evidence
axe-core verified badges for accessibility claims
Filter by category, severity, or interaction state
Page-level drill-down for every URL crawled

Desktop + mobile viewports. Focus, modal, and form validation states captured separately.

Ship-ready output

Fix-ready code

Every finding ships with code you can copy into your IDE. Not pseudocode, not suggestions. Real CSS, HTML, or JS tailored to your stack.

fix_code.css

.cta-button {
  /* Corexi fix: contrast ratio 2.8:1 → 4.6:1 */
  color: var(--color-canvas-white);
  background: var(--color-brand-deep);
  min-height: 44px;  /* WCAG 2.2 target size */
  padding: 12px 24px;
}

Design-token aware. Outputs var(--your-token) instead of hardcoded values.

app.corexi.ai

Corexi fix-ready code output showing CSS and HTML fixes

Copy to IDE

Token-aware output

app.corexi.ai

Corexi Neurodiversity Lens showing ADHD, Dyslexia, Autism, and Sensory scores

5 dimensions

ADHD · Dyslexia · Autism · Sensory · CVD

Beyond WCAG

Neurodiversity Lens

15-20% of your users think differently. The Neurodiversity Lens measures what WCAG alone can't: ADHD friendliness, dyslexia readability, autism predictability, sensory sensitivity, and color vision accessibility.

ADHD friendliness — decision paralysis, attention fragmentation
Dyslexia readability — text clarity, font choices, line spacing
Autism predictability — pattern consistency, interaction predictability
Color Vision — protanopia, deuteranopia, tritanopia safety

No extra setup. Neurodiversity scores come from your existing scan data — the engine reads your UI the way neurodiverse users experience it.

MMCP Server· before you ship

9 tools inside your IDE.

The agent that wrote the UI can ask Corexi to review it, pull UX rules, or trigger a scan. No browser tab, no copy-paste.

~/.cursor/mcp.json

Live now

{
  "mcpServers": {
    "corexi": {
      "url": "https://corexi.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer crxi_live_..."
      }
    }
  }
}

One-click install for Cursor, VS Code, Claude Desktop.
Copy-paste config for Claude Code, Windsurf, Replit.

CursorClaude CodeVS CodeWindsurfReplit

Available tools

get_ux_rulesknowledge

Proactive UX rules

Pull research-backed UX patterns BEFORE writing code.

review_codereview

Code review

Submit any snippet and get structured findings with severity, evidence, and fix code.

review_screenshotreview

Screenshot review

Upload a mockup or Figma export. Same structured review, powered by vision AI.

trigger_scanwrite

Trigger scans

Kick off a full production scan from inside the IDE.

get_findingsread

Fetch findings

Pull prioritized findings with fix code. Filter by severity, status, or interaction state.

get_ux_checklistknowledge

Surface checklists

Pre-flight checklist for 12 surface types: auth forms, checkout, modals, pricing tables.

list_sitesread

List sites

Enumerate all registered sites and their latest UX Score.

get_scan_jobread

Get scan job

Poll async scan status. Wait for completion or stream progress.

get_latest_scanread

Latest scan

Fetch the most recent scan result for any registered site.

50 free LLM reviews/month per keyFull setup guide →

Live on cursor.directory, discoverable by 80,000+ developers.

One-click install for Cursor, VS Code, Claude Desktop. Copy-paste config for Claude Code, Windsurf, Replit.

Connects to what you already use

7 analytics providers for behavioral data. 6 IDEs for developer delivery. Zero new tracking on your product.

Analytics

GA4ClarityMixpanelAmplitudePostHogFirebaseHotjar

IDEs & Agents

CursorClaude CodeVS CodeWindsurfReplitClaude Desktop

What makes it continuous

Every deploy

Scheduled scans run automatically. No manual trigger needed.

Every Monday

Weekly digest: score changes, regressing pages, priority actions in your inbox.

Every scan

Context accumulates: tech stack, tokens, behavioral signals, prior findings. Gets sharper over time.

Release tracking

Every scan is compared against the last. The dashboard is a living pulse of your product's UX health.

+14 points

over 4 scans

Where we're headed

The layer gets smarter every phase.

Each phase ships a clear, standalone capability. You get value from day one — each upgrade compounds it.

Competitive Benchmark

Building

Compare your UX Score against your industry average. See where you lead, where you lag, and what your peers are fixing.

Requires 100+ sites in the index. Growing daily.

Predictions

Planned

Industry-aware trend forecasting. Seasonal spikes, emerging UX patterns, and proactive recommendations before issues hit your metrics.

Built on scan history + behavioral signal accumulation.

Test + Compare

Planned

Generate fix variants and validate them with synthetic AI users. Measurable outcomes, not opinions.

Run variant A vs B on a new layout before you ship.

Corexi Behavioral Snippet

Live

One script tag. Instant behavioral signals. No GA4 setup, no Clarity account. Cookieless, anonymous, privacy-first.

Drop one line of code on your site. We collect scroll depth, rage clicks, bounce signals — and feed them into your UX Score.

Autofix Agent

Future

Low-risk fixes ship as Corexi-opened pull requests with your one-click approval. High-risk changes stay behind human review gates.

One-click fix execution via Cursor, Claude Code, or terminal.

Read the full vision

See it yourself.

Free in open beta. No credit card. Start with your first UX Score.

Two surfaces.One engine.

The living report that tracks your product.

UX Score at a glance

Prioritized findings

Fix-ready code

Neurodiversity Lens

9 tools inside your IDE.

Connects to what you already use

What makes it continuous

The layer gets smarter every phase.

Competitive Benchmark

Predictions

Test + Compare

Corexi Behavioral Snippet

Autofix Agent

See it yourself.

Two surfaces.
One engine.