OpenDissertation

The description states that OpenDissertation is a “space-inspired, multi-turn chat format website between Chat-GPT 5.6 and the user.” It enables users to specify one or more author-institution pairings and receive answers about selected dissertations.

It retrieves and uploads dissertations from institutional repositories (Princeton University and University of New South Wales), creates vector stores for Retrieval-Augmented Generation, and deletes files after use.

The system is built using:

• Front-end: NextJS
• Back-end: FastAPI
• Deployment: Docker containers on Google Cloud Run
• AI tools: Chat-GPT 5.6, Codex, Claude

This is a self-reported product architecture and functionality; no independent verification or data on usage exists.

The tagline states: “OpenDissertation helps you understand dissertations faster.” This reflects an intent to simplify access to long-form academic content through AI-powered interaction.

The project description indicates the authors were motivated by personal frustration with reading lengthy dissertations and wanted a tool that could answer questions instantly. The positioning is framed around convenience, speed, and accessibility of academic research.

There is no evidence of prior versions or evolution in positioning beyond this initial hackathon prototype.

The description does not explicitly define target customers or ideal customer profiles (ICP). However, it implies a use case for individuals who need to quickly access information from doctoral dissertations—likely researchers, students, or academic professionals.

No evidence of segmentation, persona development, or specific user groups is provided.

There is no evidence of any business model or pricing structure in the project description. The tool appears to be a prototype built for a hackathon and not yet monetized or offered as a service.

The authors do not mention plans for charging users, licensing, or revenue generation strategies.

• Built with NextJS (front-end) and FastAPI (back-end)
• Uses Chat-GPT 5.6 Luna Python client
• Deployed on Google Cloud Run using Docker containers
• Integrated Codex and Claude for development assistance
• CI/CD pipeline set up via GitHub actions
• Supports retrieval-augmented generation with vector stores

The authors report overcoming technical challenges such as bot protection, integration of download scripts into FastAPI endpoints, and deployment differences between local and production environments.

However, the system currently uses in-memory storage and lacks unit tests or persistent storage solutions like Redis, which are noted as future improvements.

The project is described as a hackathon submission completed within three days. It has no evidence of:

• Revenue
• Customers
• User adoption
• Product-market fit
• Long-term sustainability or growth metrics

It is not evidenced that the tool is being used outside of the hackathon context.

There is no evidence provided about existing competitors or market positioning beyond the self-reported scope of the project. No mention of similar tools, platforms, or services in the academic research space is included.

• Unverified claims: All statements are self-reported and unverified.
• No traction or revenue: The tool appears to be a prototype with no evidence of usage beyond the hackathon.
• Limited scope: Only supports two institutions (Princeton University and University of New South Wales).
• Technical limitations: In-memory storage, lack of unit tests, and reliance on AI tools for development may indicate immaturity or scalability concerns.
• No monetization strategy: No indication of how the tool would be commercialized or whether it has a viable business model.

1. What is the current status of the product beyond the hackathon? Is it being used by anyone outside of the development team?
2. How do you plan to expand support for more institutions and research formats?
3. Are there any legal or ethical considerations around downloading and processing publicly available academic content?
4. What are your plans for scaling the system, especially regarding persistent storage and performance?
5. Have you considered how this tool might be integrated into existing academic workflows or platforms?