StudyMate

StudyMate is a self-reported AI-powered study planning tool designed for working adults who study part-time while managing full-time jobs. The project was built as a submission to the OpenAI 2026 hackathon and is described by a single founder, Glenn Bak.

The product claims to convert user input (subjects, priorities, time availability) into hierarchical plans across monthly, weekly, and daily levels. It integrates AI-generated feedback and structured outputs via GPT-5.6 Terra, with validation through Zod schemas and Supabase authentication.

Key commercial due-diligence read: The description states a clear problem and solution but lacks evidence of traction, revenue, or customer adoption. There is no indication that StudyMate has moved beyond the prototype stage or has any users beyond the team itself.

Most important open question: Is there any evidence of actual user engagement or usage beyond the hackathon submission?

The description states that StudyMate:

• Converts subjects, priorities, target period, and availability into hierarchical monthly, weekly, and daily plans.
• Allows learners to record study sessions (topic, duration, understanding level).
• Provides AI-generated next actions and feedback based on completed items.
• Offers dashboards with statistics and progress tracking.
• Supports multi-provider authentication and localization in Korean and English.

It uses:

• OpenAI Responses API with GPT-5.6 Terra
• Zod schemas for structured outputs
• Supabase for social authentication
• PostgreSQL for data modeling
• Vercel for deployment

The system is described as a full responsive product, not a demo or single-prompt prototype.

Inference: The tool appears to be an AI-assisted planning and feedback loop with a UI that supports tracking and progress visualization. It integrates generative AI into a deterministic framework of time-bound planning.

The description states:

• StudyMate is positioned as an "AI study coach" for working adults.
• The tagline: “An AI study coach that turns limited time into an adaptive plan, personalized feedback, and measurable progress.”
• It aims to solve the problem of making limited weekday/weekend study time realistic and sustainable.

Inference: The positioning is clear — a productivity tool for part-time learners using AI to optimize time and provide structured feedback. The evolution from idea to product shows intent to build a complete system rather than a proof-of-concept.

The description states:

• The target user is "working adults who study alongside a full-time job."
• These users need help deciding what to study, how much time each subject deserves, and how to adjust when real life disrupts the plan.

Inference: The ICP appears to be part-time learners in professional contexts — likely students or professionals upskilling. The tool is not described as targeting full-time students or academic institutions.

The description does not state:

• Any pricing model
• Revenue streams
• Monetization strategy
• Subscription or usage-based models

Not evidenced: No evidence of a business model or pricing structure.

The description states:

• Built with OpenAI Responses API and GPT-5.6 Terra.
• Uses Zod schemas for structured outputs.
• Implements Supabase authentication and PostgreSQL.
• Delivered using Codex, Vercel, and Supabase.
• Includes multi-provider authentication, responsive UI, and localization.

Inference: The technical stack suggests a modern SaaS-like architecture with AI integration. The use of validation and retry logic implies robustness in handling generative AI outputs.

The description states:

• A complete responsive product rather than a demo.
• Multi-provider authentication, hierarchical planning, study records linked to plans, dashboards, and localization.
• The team is small (1 member).

Not evidenced: No evidence of users, customers, or adoption. The project was submitted to a hackathon — no indication it has moved beyond prototype.

The description does not state:

• Competitors
• Market positioning relative to existing tools
• Differentiation from other AI study tools or planners

Not evidenced: No competitive analysis or market context provided.

• Single founder: The team is described as a single person, which raises questions about execution capacity and scalability.
• No traction: There is no evidence of users, revenue, or adoption beyond the hackathon submission.
• Unverified AI claims: GPT-5.6 Terra is not a known model; the description may be self-reported and unverifiable.
• Prototype stage: The product is described as a hackathon submission — not a commercial product.

Inference: The risk of failure is high if no traction or user feedback emerges post-hackathon. The lack of team size and evidence of real-world usage raises concerns about long-term viability.

1. What specific problem are you solving, and how do you know it exists?
2. Have you tested the product with real users beyond the hackathon?
3. How do you plan to monetize this tool?
4. What is your roadmap for scaling beyond a single-user prototype?
5. Are there any existing tools that solve this problem, and how does StudyMate differ?