Supersede

Analysis basis

This report is based solely on the self-reported project description provided by the author. All claims are unverified and must be treated as stated by the author only.

The description states that Supersede is a TypeScript application built with Next.js 16, React 19, and PostgreSQL. It uses OpenAI’s GPT-5.6 for claim extraction, rule comparison, impact classification, case drafting, and response grading. It integrates with tools like Drizzle ORM, pgvector, Playwright, Vercel, R2-compatible storage, WorkOS, and Inngest.

It claims to:

• Extract claims from source documents.
• Map affected claims, documents, decisions, and professional roles.
• Create correction workflows involving change owners, reviewers, and experts.
• Generate checksummed audit bundles containing evidence, approvals, results, and event history.
• Enforce immutable versions and separation of duties.
• Support both human-reviewed corrections and automated dependency mapping via Propagate (a variant).

Inference The product appears to be a proof-of-concept built for a hackathon. It is not evidenced to have been used in production or deployed at scale.

The description states that Supersede was built to address the gap between updating a policy and ensuring all related documents, training modules, protocols, and people are corrected accordingly.

It positions itself as a tool for:

• Tracing the impact of policy changes.
• Ensuring corrections reach those who need them.
• Producing verifiable audit trails.

The project evolved from an idea to build a system that tracks how changes propagate through complex systems, especially in regulated industries like healthcare. The authors removed features they considered impressive but not essential — such as automated external source watching — to focus on core dependency mapping and correction workflows.

Claim

Supersede addresses a real need in policy change management.

Evidence Not evidenced. This is the author's own claim about intent and positioning.

The description mentions that Supersede was built for hospitals, specifically targeting anticoagulation policies at St. Marlowe Hospital (fictional). It also references a variant called Propagate, which focuses on correcting documents without assessing individuals.

It implies use cases in:

• Healthcare institutions.
• Regulated environments requiring compliance and auditability.
• Organizations needing to track policy impacts across multiple systems or teams.

Inference The target customer is likely large organizations with complex regulatory needs (e.g., hospitals, legal firms, government agencies).

Evidence Not evidenced. Only fictional use cases are described.

There is no mention of pricing, monetization strategy, or business model in the description.

The project is presented as a hackathon submission and includes a public walkthrough with no login required.

Claim

Supersede has a defined business model.

Evidence Not evidenced. No revenue, pricing, or customer acquisition data provided.

Supersede uses:

• Next.js 16, React 19, PostgreSQL
• OpenAI Responses API with GPT-5.6 for AI tasks
• Drizzle ORM and explicit SQL for database logic
• pgvector and Gemini embeddings for retrieval
• Playwright, Vitest, Codex for testing and development
• Vercel for hosting, R2-compatible storage for files, WorkOS for auth, Inngest for workflows

The system enforces:

• Immutable approved versions.
• Separation of duties (change owner ≠ reviewer).
• Audit trail integrity via checksummed exports.
• Structured model outputs with versioning and confidence scores.

Inference The technical stack suggests a modern SaaS architecture with strong emphasis on data integrity, auditability, and AI integration.

Evidence Based on self-reported build details.

The project is described as a hackathon demo built during Build Week. It includes:

• A public walkthrough (read-only).
• Fictional personas and scenarios.
• No real-world deployment or user feedback.

There is no evidence of:

• Customers, users, or adoption.
• Revenue or funding rounds.
• Product-market fit or traction metrics.

Claim

Supersede has demonstrated traction or maturity.

Evidence Not evidenced. It is a demo project.

The description does not reference any competitors directly. However, it implies a space involving:

• Policy change management systems.
• Compliance and audit trail tools.
• Document dependency mapping.
• AI-powered claim extraction and validation.

It builds on concepts found in:

• Regulatory compliance platforms.
• Change management software.
• Audit-ready documentation tools.

Inference Supersede may compete with or complement existing enterprise compliance, training, or change tracking systems.

Evidence Not evidenced. No competitive landscape described.

Key risks and red flags based on the description:

• The project is a hackathon demo — no evidence of real-world usage or traction.
• No pricing, monetization, or customer data.
• Claims are self-reported; no independent validation.
• The system relies heavily on AI outputs, which may not be reliable in high-stakes environments.
• Lack of real-world testing or feedback from actual users.
• No indication of scalability beyond a demo environment.

Inference The risk of overpromising and underdelivering is high due to lack of evidence for real-world utility.

Evidence Based on self-reporting only.

1. What specific regulatory or compliance challenges does Supersede aim to solve?
2. Has the system been tested in any real-world environment, even internally?
3. How is the accuracy of AI-generated claims validated in practice?
4. Are there plans for monetization or customer acquisition beyond the demo?
5. What are the key assumptions underlying the workflow design?
6. How does Supersede handle edge cases like conflicting policies or overlapping dependencies?
7. Is there any existing market demand for this type of solution, and how do you know?
8. What is the long-term vision for Supersede beyond the hackathon demo?