Show Me the Menu

Project: Show Me the Menu

Author's Self-Description: A search tool that finds restaurant menus quickly by locating the menu link directly from the restaurant's own website, regardless of where the menu actually lives.

What Changed: The project is a single-person hackathon submission built to address inconsistency in how restaurants publish their menus. It uses AI and web scraping techniques to locate and extract menu data from various sources (websites, PDFs, POS systems).

Key Open Question: Does this tool have any commercial viability or traction beyond the author's personal use case?

The description states:

• Show Me the Menu is a search tool that locates restaurant menus directly from the restaurant’s own website.
• It uses OpenAI’s API for web search, Cheerio for HTML parsing, pdf-parse for PDF extraction, and fallbacks to Toast Tab and Square menu links.
• It was built with React, Vite, Node.js, Express, and deployed as a Vercel Function.
• The tool is responsive and includes mobile/desktop support.

Inference: Based on the author's description, it appears to be a web-based menu-search utility that aggregates menu data from multiple sources using serverless infrastructure and AI-assisted search. It is not a marketplace or platform for restaurants to publish menus — rather, it’s a consumer-facing tool that helps users find existing menus.

The description states:

• The author's inspiration was the inconsistency of how restaurants publish their menus.
• The goal was to build “one tool that cuts through all of that” and provide direct access to menus without hunting.
• It is positioned as a solution for users looking for restaurant menus quickly.

Inference: This is a consumer-facing utility tool, not a B2B product. Its positioning is rooted in solving a user pain point (finding menus) rather than enabling restaurant operations or marketing.

The description states:

• The tool is designed to help users find restaurant menus quickly.
• It works by searching for menu links directly from the restaurant’s own website.

Not evidenced: No explicit customer persona, segment, or ICP defined. The author does not describe who uses it, how many users there are, or what their behavior patterns are.

The description states:

• No pricing model is described.
• It is a single-person hackathon project with no mention of monetization or revenue streams.

Inference: There is no evidence of any business model or pricing structure. The tool appears to be a proof-of-concept, not a commercial product.

The description states:

• Built with React and Vite frontend.
• Backed by Node.js and Express menu-search service deployed as a Vercel Function.
• Uses OpenAI API, Cheerio, pdf-parse, and Open-Meteo.
• Includes fallbacks to Toast Tab and Square menus.
• Responsive interface for mobile and desktop.

Inference: The tool is built with modern web technologies and serverless deployment. It uses AI for search and parsing techniques to extract menu data from various formats (HTML, PDF). It includes fallback logic for different menu delivery methods.

The description states:

• It was submitted as a hackathon project.
• The team size is 1 person.
• No mention of users, customers, or adoption.
• No revenue, ARR, or headcount data.

Not evidenced: No evidence of traction, usage, or product-market fit. The tool is described only as a prototype.

The description states:

• There is no standard way restaurants publish their menus.
• Some use embedded iframes, others link to POS systems, some upload PDFs.
• The author’s solution attempts to handle this inconsistency.

Inference: The competitive landscape includes various restaurant websites and third-party platforms (e.g., Toast, Square) that host menus. However, no direct competitors are named or described in the write-up.

The description states:

• The biggest challenge was inconsistency in how restaurants publish their menus.
• Serverless deployments behave differently from local development due to cold starts and latency.
• Restaurant websites are all structured differently.

Inference:

• Scalability Risk: The tool may not scale well due to serverless limitations and inconsistent website structures.
• Maintenance Risk: The reliance on scraping and parsing makes it fragile and hard to maintain.
• Monetization Risk: No evidence of a monetization strategy or business model.

1. What is the actual user base or adoption rate for this tool?
2. Are there any partnerships with restaurants or POS platforms already in place?
3. How does the tool handle legal and data compliance issues (e.g., scraping, copyright)?
4. Is there a plan to monetize or scale beyond the current prototype?
5. What are the long-term technical challenges of maintaining menu data from various sources?