Weavidence Journey

The description states that Weavidence Journey is a full-stack web application built around a deterministic decision engine, not a generative chatbot. It guides users through seven lifecycle stages:

1. Intake
2. Guided Questions
3. Path & candidate designs
4. Protocol Modules
5. Review & Save
6. Protocol Preview
7. Export

It supports multiple methodological paths and presents candidate study designs with visible rationale, allowing researchers to confirm or override decisions while keeping important choices traceable.

The system includes:

• Structured semantic registry for questions, concepts, answers, study designs, and methodological contracts.
• Deterministic routing across methodological paths.
• Candidate-design evaluation and transparent rationale.
• Human confirmation and justified override workflows.
• Selective invalidation when upstream answers change.
• Revision-aware review and evidence binding.
• Professional protocol generation and export in formats like JSON, HTML, PDF, DOCX.

The author notes that AI (GPT-5.6 and Codex) was used for engineering support but not as the runtime scientific authority; final decision-making remains with the human researcher.

Evidence strength Evidenced from self-report only.

The project is positioned as a tool for creating auditable research protocols, emphasizing:

• Deterministic, human-controlled journeys.
• Transparent guidance and traceable decisions.
• Professional outputs (structured JSON, HTML, PDF, DOCX).
• Audit history and decision traces.
• Separation of methodological quality indicators (Decision Score, Design Fit, Readiness).

It is described as addressing a gap in current tools: general-purpose AI can draft text but cannot govern methodological processes.

The author claims that the tool does not collapse uncertainty into one definitive answer, instead separating candidate designs, fit, methodological quality, readiness, caveats, and human confirmation.

Evidence strength Evidenced from self-report only. No third-party validation or market positioning data provided.

The target customer is described as researchers, particularly those working in public health and epidemiology. The author identifies themselves as an epidemiologist and public-health professional who has seen research protocols written as documents without explicit methodological decisions being made visible.

There is no mention of specific user personas, segments, or use cases beyond the general category of researchers needing to build structured, auditable protocols.

Evidence strength Evidenced from self-report only. No evidence of customer interviews, market segmentation, or competitive targeting.

No information is provided about pricing models, monetization strategies, or business model assumptions. The project description does not include any claims regarding revenue streams, subscription tiers, licensing, or commercial partnerships.

Evidence strength Not evidenced.

The application is built using:

• Frontend: React, TypeScript, HTML5, CSS3
• Backend: Node.js, Express, Prisma, PostgreSQL
• DevOps: Docker, Vercel, Render, GitHub Actions
• AI tools: GPT-5.6, Codex, Playwright, Vitest
• Authentication: OAuth
• APIs: REST, OpenAI API

The system supports:

• Automated unit, integration, browser, semantic, and regression testing.
• Semantic registry for questions, concepts, answers, study designs, and methodological contracts.
• Revision-aware review and evidence binding.
• Export of professional outputs including structured JSON, HTML, PDF, DOCX.

It is described as a production-ready web architecture with adversarial validation and negative testing practices.

Evidence strength Evidenced from self-report only. No data on performance metrics, scalability, or deployment history.

There is no evidence of traction, revenue, customers, or adoption beyond the author’s own development work. The project was not presented as having launched or being used in real-world settings prior to or during the hackathon.

The author states that the system existed before the hackathon and underwent a major refactoring during Build Week, but there is no indication of user feedback, usage statistics, or product-market fit validation.

Evidence strength Not evidenced.

No mention of competitors or competitive landscape. The description does not reference existing tools for research protocol design, methodological guidance, or scientific workflow management.

Evidence strength Not evidenced.

• Lack of external validation: No evidence of real-world usage, customer feedback, or product-market fit.
• Single-founder development: The team size is listed as one member (VaX1989 CORONA), raising questions about scalability and long-term maintenance.
• Unproven market demand: The author’s own experience is the only context for the tool’s utility; no third-party validation or market research is presented.
• AI dependency without clarity on autonomy: While AI was used in development, it is unclear how much of the runtime functionality relies on AI, and whether this could be a risk if AI access changes.
• Highly specialized domain: The focus on epidemiology and public health may limit broader applicability unless expanded.

Evidence strength Inferred from lack of evidence and self-reporting limitations.

1. What specific research workflows or problems does the tool aim to solve, and how do you know these are real needs?
2. Have you tested the system with actual researchers outside of your own development process?
3. How is the methodological content validated? Is there domain expertise embedded in the design?
4. What would constitute success for this product beyond its current prototype stage?
5. Are there any early adopters or pilot users who have provided feedback?
6. How do you plan to scale beyond a single developer’s capacity?
7. What are your thoughts on integrating with existing research infrastructure or platforms?

Evidence strength Inferred from lack of evidence and need for deeper exploration.