Each persona is grounded in cognitive science research, traces your actual code paths, and reports what real users would experience. In parallel. In 2 minutes.
Traditional studies take weeks, cost thousands, and arrive after the code has shipped. UTA runs in your editor, on your code, in minutes.
Use as a Claude Code plugin or connect via MCP to any AI editor.
Connect UTA to any MCP-compatible AI tool. Your code stays local. Your AI subscription does the work.
uta_test — full 9-persona test
uta_test_quick — 3-persona quick check
uta_test_persona — single persona deep dive
uta_list_personas — browse all personas
uta://personas — overview of all 9
uta://persona/{id} — full persona definitions
uta://scoring-model — scoring framework
uta://domain-template — config template
The MCP server provides instructions. Your AI tool reads your code locally. Nothing leaves your machine.
Once cloned and built, no external dependencies. No API keys to configure. No accounts to create.
Not demographic personas. Behavioral archetypes derived from cognitive science — how people actually interact with interfaces.
Every problem type is covered by multiple personas. The matrix shows primary focus and secondary coverage.
| Problem Type | Scanner | Deliber. | Pragm. | Novice | Power | Multi. | A11y | Eval. | Purist |
|---|---|---|---|---|---|---|---|---|---|
| Dead-end flows / no path forward | |||||||||
| Broken handlers / silent failures | |||||||||
| Jargon / technical language | |||||||||
| Missing empty states | |||||||||
| Missing keyboard shortcuts | |||||||||
| Lost form state / no autosave | |||||||||
| Accessibility failures (ARIA, focus, contrast) | |||||||||
| Irreversible actions / no undo | |||||||||
| Excessive steps / slow paths | |||||||||
| Spacing / typography / alignment issues | |||||||||
| Missing loading / error states | |||||||||
| Credibility / trust signals missing | |||||||||
| Edge case failures (extreme inputs) | |||||||||
| No onboarding / guidance |
Every test run produces a unified report with scores, ranked issues, and actionable solutions. Here's a real example structure.
| Persona | Effect. | Effic. | Learn. | Satis. | Craft | Composite |
|---|---|---|---|---|---|---|
| Scanner | 85 | 78 | 70 | 80 | 65 | 77 |
| Deliberator | 80 | 65 | 82 | 78 | 72 | 76 |
| Rushing Pragmatist | 70 | 60 | 55 | 68 | 60 | 63 |
| Novice | 55 | 50 | 45 | 52 | 60 | 50 |
| Power User | 88 | 82 | 75 | 85 | 70 | 81 |
| Distracted Multi. | 45 | 40 | 50 | 42 | 60 | 44 |
| Accessibility User | 62 | 58 | 65 | 60 | 55 | 60 |
| Skeptical Eval. | 78 | 70 | 75 | 72 | 68 | 73 |
| UI Purist | 80 | 75 | 78 | 82 | 62 | 73 |
| Dimension | Avg | Weakest | Strongest | Systemic? |
|---|---|---|---|---|
| Effectiveness | 71 | Distracted Multi. | Power User | Yes |
| Efficiency | 64 | Distracted Multi. | Power User | Yes |
| Learnability | 66 | Novice | Deliberator | Yes |
| Satisfaction | 69 | Distracted Multi. | Power User | Partial |
| Craft | 64 | Accessibility | Deliberator | Partial |
| Flow | Scan | Del | Prag | Nov | Pow | Mul | A11y | Eval | Pur | Cov. |
|---|---|---|---|---|---|---|---|---|---|---|
| Chart creation | x | x | x | x | x | x | x | x | x | 9/9 |
| Data input (paste) | x | x | x | x | x | x | 6/9 | |||
| Export PDF | x | x | x | x | x | x | x | 7/9 | ||
| Theme switching | x | x | x | x | 4/9 | |||||
| Report builder | x | x | x | x | 4/9 | |||||
| Settings | x | x | x | 3/9 | ||||||
| Admin panel | 0/9 | |||||||||
| User preferences | 0/9 |
Every persona's existence is provable, not just theoretically motivated. Challenge any persona — the data backs it up.
Each persona scores across 5 dimensions with persona-specific weight adjustments. The Novice weights Learnability at 35%. The UI Purist weights Craft at 50%.
UTA personas are calibrated for products where users navigate pages, fill forms, click buttons, read content, and expect professional output.
Dashboards, admin panels, analytics tools, CRM, project management. All 9 personas are calibrated for this. Every checklist item applies.
Built without design resources, rarely usability tested. Highest ROI — Novice and Scanner catch the most issues here.
Checkout flows, product browsing, search, filtering. Rushing Pragmatist catches cart friction. Skeptical Evaluator catches trust gaps.
CLIs with web UIs, API dashboards, documentation platforms. Power User catches missing shortcuts. Novice catches bad onboarding.
Scanner + Skeptical Evaluator + UI Purist are highly relevant for conversion optimization and credibility assessment.
Navigation, readability, accessibility, and content management flows. Deliberator and Accessibility User add the most value here.
9 personas. 5 dimensions. 14 problem types. One command.