Supervisor Outreach Agent

What the company appears to be: A self-reported AI-powered platform for academic applicants seeking supervisors for Master's and PhD programs. It claims to automate discovery, analysis, and ranking of university supervisors based on applicant profiles.

What changed: The project was submitted to the OpenAI 2026 hackathon, indicating it is a prototype or early-stage product with no evidence of commercial traction or deployment.

Single most important open question: Is there any evidence of actual user adoption, revenue, or customer validation beyond the hackathon submission?

The description states: “A multi-agent AI system that discovers universities, finds supervisors, analyzes research, and ranks the best academic matches for Master's and PhD applicants.”

• Evidenced: The product is described as a multi-agent AI system.
• Inferred: It operates in the academic admissions space, targeting graduate-level applicants.
• Not evidenced: No details on how the system works, what data it uses, or whether it has been deployed.

The author states: “A multi-agent AI system that discovers universities, finds supervisors, analyzes research, and ranks the best academic matches for Master's and PhD applicants.”

• Evidenced: The positioning is to automate academic match-making for graduate-level applicants.
• Inferred: The product aims to reduce friction in the supervisor-search process for students.
• Not evidenced: No evidence of prior versions, market testing, or evolution from an earlier idea.

The description states: “for Master's and PhD applicants.”

• Evidenced: The target customer is graduate-level academic applicants.
• Inferred: The product may be aimed at students in STEM fields who are seeking research supervisors.
• Not evidenced: No evidence of specific demographics, geographic focus, or user personas.

The description states no information about pricing or business model.

• Not evidenced: No mention of monetization strategy, subscription tiers, or revenue streams.
• Inferred: If commercialized, it might be a SaaS or freemium model, but this is speculative.

The author-declared tech stack includes: api, asgi, asyncio, css, fastapi, gpt, next.js, openai, python, react, tailwind, typescript, uvicorn.

• Evidenced: The system uses Python, React, Next.js, OpenAI APIs, and FastAPI.
• Inferred: It is likely a web-based application with AI integration for academic matching.
• Not evidenced: No evidence of deployment, scalability, or production readiness.

The project was submitted to the OpenAI 2026 hackathon on Devpost.

• Evidenced: The product is a hackathon submission.
• Inferred: It has not been validated in a real-world environment or with paying customers.
• Not evidenced: No evidence of user engagement, customer feedback, or product iteration.

The description does not mention any competitors.

• Not evidenced: No information on existing solutions in the academic match-making space.
• Inferred: There may be no direct competitors if this is a novel idea, but that cannot be confirmed from the description alone.

• The product is described as a hackathon submission with no evidence of commercialization or traction.
• No pricing, revenue, or customer data are provided.
• The team size is small (4 members), which may limit execution capacity.
• The lack of a detailed write-up suggests limited development beyond prototype stage.

1. What is the current stage of development? Is this a working prototype or a concept?
2. Have you tested the system with real users or academic applicants?
3. How do you plan to monetize the product if it gains traction?
4. What are the main technical challenges in scaling this system for global use?
5. Are there any partnerships or collaborations with universities or research institutions?