| What it does | Run structured AI debates, pitch reviews, focus groups, audience simulations and idea tournaments with inspectable transcripts and reports
| UI components, templates and Skills for AI models to deliver professional-grade work
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Not given
| Builder: ¥45/month, ¥128/quarter, ¥379/year. Includes unlimited copy and install, 8pt MCP, all components, templates, themes, icons, and Skills. Builder + AI coming soon: ¥959/year. Team coming soon: ¥479/seat/year for 2 to 50 seats.
|
|---|
| Key features | - Decision stress-test with opposing agents and convergence recommendation
- Judged debate with neutral arbiter scoring
- Expert panel with key insights without verdict
- Focus group with moderated discussion guide and verified quotes
- Idea tournament with bracket and kill cards
- TribeMind synthetic audience with opinion tracking
- Shark Tank pitch panel with cross-examination
- Interview simulator for testing guides on simulated participants
- MultiFormat workflow chaining multiple formats together
- Support for major AI models including Anthropic, OpenAI, Google Gemini, and others
| - 42 ready-to-use UI components with live preview and full source code
- Full-page templates that work immediately
- Skills library for models to follow professional workflows
- Unified theme system with variable-based design tokens
- 48 original icons with consistent line weight and 24px grid
- MCP integration for Claude Code, Cursor, Codex, and Trae
- Prompt copying and component installation across multiple AI models
- Native HTML, CSS, and JavaScript source code with no hidden dependencies
- CLI access for terminal-based component installation
- Personal collections with project-based organization
|
|---|
| What makes it different | - Structured protocol determines turn order, not model inference
- Each participant has separate briefs and private context
- Persistent transcripts preserved turn by turn
- Human steering mid-discussion without restarting
- Multiple dissenting AI perspectives instead of single framing
| - Works with any text-capable AI model, not locked to one platform
- Single prompt works across different models and editors from terminals to code editors
- Real source code that adapts to each project's design system and framework
- Same components look completely different across projects through themes and design variables
- Commercial use allowed for copied or installed code in own projects
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 4 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 0 |
|---|
| Citation Flow (Majestic) | 11 | 0 |
|---|
| Referring domains (Majestic) | 1 | 0 |
|---|
Delibora
8pt