| What it does | AI-native productivity suite for turning ideas into projects with working prototypes
| A Claude Desktop extension and plugin that convenes a council with ChatGPT and Gemini for independent AI positions, votes, and recorded dissent
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| DE
|
|---|
| Pricing model | Paid
| Paid
|
|---|
| Pricing | $20 USD per person per month, plus per-job charges: Chat included; Handoff note $0.25; Workspace upload and storage $0.25; Decision plan $0.75; Single document $0.75; Competitive analysis $1.00; Cluster map $1.00; Idea batch (10 ideas) $1.50; Working preview build $1.50; Strategy analysis $3.00; Doc
| One-time purchase for Claude Desktop and Claude Code. Usage costs paid directly to OpenAI and Google: $0.02–$0.15 per council decision depending on effort tier and input size; image generation $0.05–$0.20 per call.
|
|---|
| Key features | - Wizard: shapes ideas, suggests startup directions, learns user taste
- Way: tracks decisions, analyzes outcomes, measures work against North Star
- Workspace: organizes files, writes documents from context, builds working preview
- Wire: routes team chat, direct messages, and agent notifications in one stream
- Whiteboard: shared visual canvas for mapping ideas and shaping plans
- World: tracks markets, competitors, and outside changes for informed decisions
- Integrates with Grok Bot, Muse, Claude, Codex, and Cursor agents
- Connected agents get scoped live stream of project signals and changes
- Weekly review emails summarize changes and work needing attention
- Project assistant answers questions about open projects
| - Three independent AI positions on questions
- Majority voting with dissent recorded
- Budget guard with daily spending limit
- Integrates ChatGPT, Gemini, and Claude
- Runs on Claude Desktop (macOS, Windows) and Claude Code
- Uses own API keys with secure OS storage
- Nine specialized tools for different decision types
- Two-round cap and domain tie-break for consensus
- Failure handling and 345 tests
- Plain-language interface requiring no developer skills
|
|---|
| What makes it different | - Turn ideas into working prototypes in under five minutes with AI agents
- Every decision recorded with its reasoning and context for full traceability
- Visual layers for agents similar to design and project management tools
- Coordinates work across people, agents, workflows, and automations in one place
- Builds live web versions of projects shareable and testable on any device
| - Three independent AI models vote together with dissent kept on record, avoiding single-model bias
- Budget guard prevents runaway bills with daily ceiling and worst-case cost reserving
- Uses your own API keys stored securely locally, no server or data transmission
- One-time purchase model with no subscription or ongoing fees
- Works directly in Claude without developer skills
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 32 ▼ −1 (down) since last check | 12 ▲ +10 (up) since last check |
|---|
| Trust Flow (Majestic) | 2 | 1 |
|---|
| Citation Flow (Majestic) | 23 | 21 |
|---|
| Referring domains (Majestic) | 14 | 3 |
|---|
Ask The W
Kirat