WeDig

The description is self-reported and unverified. This analysis is based entirely on the project description provided by the caller — no archived data, third-party sources, or independent verification are available.

The description states that WeDig is:

• A governed collaboration room where multiple AI sessions can work together.
• Each participant brings their own AI account and quota.
• Participants sign in via GitHub and request access to a shared room.
• Hosts define goals, completion criteria, and approve access.
• Agents propose roles, but these must be ratified by the host before tasks are assigned.
• Work produces task-linked artifacts that can be reviewed, challenged, and revised.
• Final publication decisions remain with a human.
• Artifacts are stored with metadata including revision history, SHA-256 digests, and authorship.
• The system uses SQLite, Next.js, React, Phaser.js, Playwright, and MCP (Model Context Protocol).

This is a self-reported description of the product. No evidence of actual deployment or user behavior is provided.

The author claims that WeDig:

• Solves the problem of AI collaboration in classrooms where students have individual accounts but cannot coordinate effectively.
• Does not pool subscriptions, bypass quotas, or share credentials.
• Preserves artifact bytes, revision history, and peer review.
• Turns AI collaboration from "copied prompts" into a system with visible ownership, bounded authority, and accountable publication.

The positioning is framed as a privacy-preserving, human-in-the-loop, and collaboration-focused tool for small teams or educational settings. It emphasizes:

• Explicit consent
• Scoped authority
• Artifact integrity
• Human finality

These are claims made by the author, not verified facts. The product is positioned as a solution to coordination challenges in AI workflows, but no evidence of market traction or customer feedback exists.

The description states that WeDig is intended for:

• AI classrooms
• Small software teams
• Game-development groups
• Interdisciplinary communities where work is fragmented across independently owned sessions

It also notes that the system is designed to be scalable to other participant-owned AI runtimes, while preserving human boundaries.

The target customer segment is self-defined. No evidence of actual customers, usage data, or market validation is provided.

There is no mention in the description of:

• Revenue streams
• Pricing models
• Monetization strategy
• Customer acquisition costs
• Unit economics

Not evidenced.

The project was built with:

• Frontend: Next.js, React, Phaser.js, TypeScript
• Backend: Node.js 22, SQLite
• Tools: GitHub OAuth, Playwright, Codex (via GPT-5.6), MCP protocol
• Infrastructure: Cloudflare Tunnel, OpenAI integration

Key technical elements include:

• A room-scoped filesystem for artifact storage
• REST and MCP adapters for canonical collaboration state
• A resident connector that exchanges launch codes for scoped authority
• Support for finite Codex work cycles
• Use of SHA-256 digests to identify reviewed bytes

The technical stack is described, but no evidence of production deployment or scalability is provided.

The description includes:

• A live product URL: https://wedig.dev
• A public repository: https://github.com/jys20240601/openai-buildweek
• A demo video: https://youtu.be/3ajPesx354o
• Mention of a Phase 6 evaluation contract for testing scenarios

However, there is no evidence of:

• User base or active adoption
• Revenue or monetization
• Customer feedback or testimonials
• Product usage metrics
• Iteration history beyond the hackathon submission

Not evidenced.

The description does not mention any direct competitors. It positions WeDig as a solution to coordination issues in AI workflows, particularly where individual accounts are used and credential sharing is avoided.

No competitive landscape or market positioning against existing tools is provided.

• No real-world usage: The product appears to be a hackathon submission with no evidence of adoption.
• Unproven scalability: The architecture targets small rooms, not internet-scale concurrency.
• Self-reported success: All claims are based on the author’s own account; no independent validation or feedback is provided.
• Limited commercial viability: No pricing, revenue, or customer data is available.
• No third-party integration: The system relies heavily on participant-owned AI sessions and does not appear to integrate with broader AI ecosystems.

These are inferences based on the lack of evidence for real-world use or traction.

1. What is the actual user base or adoption rate beyond the hackathon?
2. How do you plan to scale beyond small rooms and classroom settings?
3. Are there any plans for monetization or revenue generation?
4. How does WeDig handle edge cases like failed tasks, interruptions, or conflicting reviews?
5. What are the limitations of the current architecture in terms of performance or reliability?
6. Have you tested the system with real users outside of the development team?
7. Is there a roadmap for integrating with other AI platforms or tools?