Matsuri Schedule Catcher

• The description states that Matsuri Schedule Catcher is a searchable festival directory for Aichi, Gifu, Mie, and Shizuoka.
• It allows filtering by prefecture, date, festival type, and keyword.
• Users can view detail pages with highlights, access, parking, rain policy, organizer, and source information.
• The product has two modes:
  • Sample mode: No code required; uses rule-based extraction; leaves unknown fields empty.
  • Judge-only live mode: Sends an announcement to GPT-5.6 Luna through OpenAI Responses API after validating a judge access code.
• Both modes lead to the same human review screen where all fields are editable.
• Confirmed records are stored in browser localStorage only.
• The system uses Zod for schema validation and includes checks for duplicates, required fields, and format compliance.

Inference: The product is not a live service but a demonstration of how AI could be used to extract structured data from unstructured festival announcements. It is described as an MVP built for a hackathon with no production deployment or user base beyond the demo.

• The description states that festival information across Japan’s Tokai region is scattered and difficult to find.
• The core principle is: “AI can organize the announcement, but a person remains responsible for checking the result and its source.”
• It positions itself as a tool that organizes data without treating AI output as automatically trustworthy.
• The product claims to make festival discovery easier by centralizing information in one place.

Inference: This is a self-reported positioning claim. There is no evidence of market traction, customer feedback, or competitive differentiation beyond the hackathon context.

• The description states that the target region is Japan’s Tokai region (Aichi, Gifu, Mie, Shizuoka).
• It appears to be aimed at individuals looking for festival information in this area.
• There is no indication of a specific persona or buyer profile beyond general users seeking event details.

Inference: No evidence of defined ICP or target user segmentation beyond the geographic scope. The product is described as a demo, not a commercial offering.

• Not evidenced.
• The description does not mention any pricing structure, monetization strategy, or business model.
• It is described as a hackathon project with no revenue or customer data.

Inference: No evidence of a business model or pricing mechanism. The product is presented as an MVP for demonstration purposes only.

• Built with Next.js App Router, React, TypeScript, Tailwind CSS, Zod, Vitest, OpenAI JavaScript SDK, Responses API, Structured Outputs.
• Uses gpt-5.6-luna model via the OpenAI Responses API.
• Implements schema validation using Zod for both transport and business-level data.
• Includes rate-limiting, input size limits, and security controls (e.g., no exposure of API keys or judge codes).
• Has a clear separation between sample and live modes.
• Uses localStorage for temporary storage; no database or backend persistence is mentioned.
• The project includes 32 passing tests, linting, typechecking, and a production build.

Inference: Technical implementation shows some sophistication in handling AI integration, validation, and security. However, it lacks real-world deployment or scalability features like persistent storage or multi-user support.

• Not evidenced.
• The product is described as a hackathon submission with no mention of users, customers, or adoption metrics.
• It uses fictional data for demonstration purposes.
• No evidence of revenue, ARR, or usage statistics.

Inference: There are no signs of traction or maturity beyond the initial demo. The project is clearly in an early stage and not yet a product in production use.

• Not evidenced.
• The description does not reference existing competitors or similar tools.
• No market analysis or competitive positioning is provided.

Inference: No evidence of competitive landscape or differentiation from other event discovery platforms. This is a self-contained project without external context.

• No traction or revenue: The product is described as a hackathon demo with no real-world usage.
• Limited scope: Only covers the Tokai region and uses fictional data.
• No persistence: Data is stored only in browser localStorage, not in any backend system.
• No monetization strategy: No indication of how this would become a sustainable business.
• AI dependency without oversight: While human review is required, the reliance on AI for extraction introduces risk if the model fails or produces inaccurate data.
• Sample vs. live mode confusion: The distinction between sample and live modes may not be clear to end users in a real product.

Inference: These are risks inherent to an MVP built for a hackathon, but they are not validated by any external data.

1. What is the plan to move from this demo to a production-ready service?
2. Are there plans to expand beyond the Tokai region or add more features like maps, notifications, or multilingual support?
3. How will you ensure data accuracy and prevent misuse of AI-generated content?
4. Is there any intention to monetize this product? If so, how?
5. What are the long-term goals for user engagement or retention?
6. Are there any partnerships with local municipalities or tourism boards that could drive adoption?