Archive position — measured, not model output
0 likes on Devpost
2,264 of the 7,856 archived projects have more likes, and 5,592 share exactly 0 — so this project's #7,098 place in the like-ranked listing is a tie-break inside that group, not a ranking.
Projects (log scale)
Likes on Devpost. ▲ marks this project's group.
Show the figures
| Likes | Projects | Share of archive |
|---|---|---|
| 0 | 5,592 | 71.2% |
| 1 | 1,758 | 22.4% |
| 2 | 285 | 3.6% |
| 3–4 | 132 | 1.7% |
| 5–9 | 75 | 1.0% |
| 10+ | 14 | 0.2% |
Executive Summary
What the company appears to be
SynThesis is an AI-powered research assistant for students exploring thesis topics. The description states it uses archived thesis records and AI models (GPT-5.6-sol, text-embedding-3-small) to help users search, retrieve, and generate structured guidance on previous research.
What changed
This is a hackathon project submitted to the OpenAI 2026 hackathon. It has no evidence of commercial traction, revenue, or customer adoption beyond its own self-description.
Single most important open question
Is there any evidence that this system works in practice, or whether it can scale beyond a prototype?
What The Product Actually Is
The description states that SynThesis is an AI-powered thesis research assistant. It helps students explore previous research thesis records and faculty research works by:
- Searching for topics using meaning-based retrieval (not just keywords)
- Using GPT-5.6-sol to generate structured research guidance
- Providing a catalog of thesis records, adviser recommendations, methodology reports, and knowledge maps
The system uses FastAPI backend, JSON dataset, text embeddings, and OpenAI models.
Evidence The project description states this.
Inference This is a prototype or proof-of-concept built for a hackathon.
Positioning & Claim Evolution
The description states that SynThesis was inspired by students' difficulties in finding thesis topics, related studies, and mentors. It positions itself as an intelligent research assistant that turns archived thesis records into useful information for decision-making.
Evidence The project's "Inspiration" section claims this.
Inference This is a self-reported positioning statement, not validated traction or market feedback.
Target Customer & ICP
The description states that SynThesis helps students exploring thesis topics. It also mentions helping students find related studies and identify suitable mentors.
Evidence The project's "Inspiration" section claims this.
Inference The target is likely graduate or postgraduate students, but no evidence of specific customer segments or personas.
Business Model & Pricing Evidence
Not evidenced.
Explanation
The description does not mention any pricing, monetization strategy, or business model.
Technical & Delivery Signals
The system was built using:
- FastAPI backend
- JSON dataset of thesis records
- OpenAI models (GPT-5.6-sol, text-embedding-3-small)
- Text embedding for semantic search
- Structured prompts to ensure grounded responses
It includes fallback mechanisms for AI failures and keyword-based search.
Evidence The "How we built it" section states this.
Inference This is a technical prototype, not a production system.
Traction & Maturity Signals
Not evidenced.
Explanation
There is no evidence of revenue, customers, usage metrics, or product adoption beyond the hackathon submission.
Competitive Context
Not evidenced.
Explanation
No mention of competitors, market size, or competitive positioning in the description.
Key Risks & Red Flags
- Prototype only: Built for a hackathon; no evidence of production readiness or real-world use.
- Unverified AI outputs: The system uses GPT-5.6-sol but does not demonstrate accuracy or reliability of its outputs.
- No data sources or scale: The description mentions JSON files and embeddings, but no indication of how large or diverse the dataset is.
- No commercial viability: No evidence of monetization, pricing, or customer base.
Diligence Questions To Ask The Founders
- What is the actual size and quality of the thesis dataset used?
- How does the system handle ambiguity or conflicting information in the archive?
- Has the prototype been tested with real students or researchers?
- Are there any plans to expand beyond academic use cases?
- Is there a path to monetization or scaling beyond the hackathon version?
Investment/Partnership Verdict
Not evidenced.
Explanation
There is no evidence of revenue, traction, or commercial viability. The project is described as a hackathon submission with no indication of future development or market readiness.
Confidence level Low — based entirely on self-reported description with no external validation.
Source
Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.
The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.