MEET

The description states that MEET is a tool designed to help users discover and attend events they might otherwise miss, using AI-driven personalization and event aggregation from multiple sources including RSS feeds, Eventbrite, and web crawling. The author claims it was built with AI assistance (Codex, GPT-5.6, Groq), Next.js, Supabase, Exa, and Leaflet maps. It allows users to upload resumes and express preferences, then ranks events based on relevance and location.

The project appears to be a solo effort by Naavya Vig, submitted as part of the OpenAI 2026 hackathon. The author describes MEET as a tool that could make a real impact by connecting ambitious creators with relevant opportunities, but no evidence of revenue, customers, or adoption is provided. The product is described as a full-stack app with personalization features and event quality-checking via AI.

The single most important open question is: What is the actual commercial viability of MEET's approach to event discovery and personalization? The description does not provide evidence of any traction, monetization strategy, or clear path to scale beyond the hackathon context. The author’s own account suggests a vision for expanding into a professional social network, but this remains unproven.

The description states that MEET is an event discovery tool that aggregates events from multiple sources—RSS feeds, Eventbrite, and web crawling—and uses AI to personalize and rank them based on user preferences and location. It allows users to upload resumes and express interests, then provides a feed of relevant events.

It was built using:

• Codex for code generation
• GPT-5.6 for planning and design decisions
• Groq’s Llama model for resume parsing and event matching
• Next.js for frontend
• Supabase Auth/Postgres for backend
• Exa web discovery
• Leaflet maps

The app uses deterministic code for filtering, ranking, deduplication, and explanations. It includes a clean UI with tracing for each event.

The description states that MEET was inspired by the author’s own experience of missing an OpenAI build week event due to lack of awareness. The core claim is that there are many talented people restricted by lack of access to events they want to attend, and MEET aims to solve this.

The positioning appears to be:

• A tool for ambitious builders, innovators, and creators
• Focused on helping users discover relevant events across platforms
• Leveraging AI for personalization and quality-checking

The author claims the app is “a real tool that so many people in the world could use to make a real impact.” The vision includes expanding into a professional social network similar to LinkedIn but focused on events, and adding different niches beyond CS/STEM.

The description states that MEET targets "ambitious builders, innovators, and creators," particularly those in the AI and tech space. It is positioned for people who want to attend events they might otherwise miss due to lack of awareness or access.

The author notes a focus on professional events, especially in CS/STEM fields, but also mentions plans to expand into other niches. The user base would likely include individuals seeking career development, networking opportunities, and learning experiences.

Not evidenced.

The description does not contain any information about pricing models, monetization strategies, or business model assumptions. No evidence of revenue streams, subscription tiers, or commercial arrangements is provided.

The description states that MEET was built using:

• Codex for code generation and bug fixing
• GPT-5.6 for planning and feature improvements
• Groq’s Llama model for AI tasks like resume parsing and event matching
• Next.js, Supabase Auth/Postgres, Exa web discovery, Leaflet maps

It uses deterministic code for:

• Distance filtering
• Ranking
• Deduplication
• Transparent explanations

The system includes RLS-protected user data and a compliant, evidence-backed event pipeline.

Not evidenced.

There is no evidence of users, customers, or adoption. The description states that the project was submitted to the OpenAI 2026 hackathon, but does not indicate whether it has been deployed beyond that context or if there are any active users or metrics.

The description states that existing platforms like Luma and Eventbrite exist but are limited to their own events—not all available events. MEET aims to address this gap by aggregating from multiple sources including web crawling, RSS feeds, and Eventbrite.

No specific competitive analysis is provided beyond this general comparison. The author does not name direct competitors or describe market share or positioning relative to existing players.

• Solo development: The project was built by a single person (Naavya Vig), which raises questions about scalability, maintenance, and long-term viability.
• Unproven commercial model: There is no evidence of revenue, pricing, or monetization strategy.
• Technical challenges: The description notes difficulties with web crawling, quality-checking events, and delays in pulling events from the internet—these could indicate technical limitations or scalability issues.
• Lack of traction: No evidence of users, customers, or adoption beyond a hackathon submission.
• AI dependency: Heavy reliance on AI tools (Codex, GPT-5.6, Groq) may raise concerns about consistency and cost as the product scales.

1. What is the current status of MEET? Is it deployed beyond the hackathon?
2. How does MEET plan to monetize its service?
3. What are the specific challenges with web crawling and event quality-checking that were mentioned?
4. Has there been any user feedback or testing beyond the author’s own experience?
5. What is the long-term vision for MEET, particularly around expanding into a social network?
6. How does MEET handle data privacy and compliance in its event pipeline?
7. What are the key assumptions underlying the personalization algorithm?