OpenAI 2026 hackathon

ClaireSante

ClairSortie turns complex hospital discharge documents into clear, traceable action plans, highlights uncertainties, and helps patients understand what to do next.

Solo project by Marc VAN DRIESTEN · 0 likes · 0 comments

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 #3,277 place in the like-ranked listing is a tie-break inside that group, not a ranking.

Projects (log scale)

1
10
100
1k
10k
05,592
11,758
2285
3–4132
5–975
10+14

Likes on Devpost. ▲ marks this project's group.

Show the figures
LikesProjectsShare of archive
05,59271.2%
11,75822.4%
22853.6%
3–41321.7%
5–9751.0%
10+140.2%
Devpost like counts for all 7,856 archived projects, captured when this archive was built.

Executive Summary

ClaireSante (formerly ClairSortie) is a self-reported prototype that processes hospital discharge documents into structured, readable action plans using web technologies and AI. The author states it aims to simplify complex medical information for patients post-hospitalization, with emphasis on transparency, source citation, and safety constraints.

The project is described as a hackathon submission, built with HTML, CSS, JavaScript, and Python, hosted via GitHub Pages, and not yet validated or deployed in clinical settings. It currently lacks revenue, customers, or traction data beyond its own description.

Key open question: Is there any evidence that the author has begun testing the prototype with actual healthcare professionals or patients, or that they have moved beyond a proof-of-concept stage?

Back to contents

What The Product Actually Is

The description states that ClaireSante allows users to paste synthetic or anonymized hospital discharge documents and generates:

  • A simple next-step action plan;
  • Medication changes and follow-up tasks;
  • Original source passages for each extracted item;
  • Questions to ask healthcare professionals when information is unclear;
  • A short comprehension quiz;
  • Structured JSON data.

The application does not diagnose, prescribe, or replace a healthcare professional. It is described as a mobile-first web demonstration built with HTML, CSS, and JavaScript, and also includes a Python MVP using Gradio, pypdf, Pydantic structured data, automated tests, and an optional OpenAI API extraction path.

Inference: The product appears to be a document processing tool that extracts structured information from unstructured medical text. It is not a device or service but a software prototype.

Back to contents

Positioning & Claim Evolution

The author states the inspiration behind ClaireSante was to address the difficulty patients face in understanding discharge instructions after hospital stays, especially when tired or in pain.

The product is positioned as a tool that turns complex documents into clear action plans while highlighting uncertainties and preserving source citations. It explicitly avoids providing medical advice or diagnosis.

Inference: The positioning is centered on patient empowerment through clarity and transparency, not on replacing healthcare professionals or offering diagnostic capabilities.

Back to contents

Target Customer & ICP

The description states the target users are patients who have recently been discharged from hospitals and struggle to understand their discharge instructions. These patients may be tired, stressed, or in pain, making it harder for them to process complex information.

Inference: The primary customer is a patient segment with limited health literacy or cognitive capacity during recovery, not healthcare providers directly.

Back to contents

Business Model & Pricing Evidence

There is no evidence of pricing, revenue streams, or business model in the description. The author states that the project is currently a hackathon prototype and not a validated medical device.

Not evidenced: No indication of monetization strategy, customer acquisition plan, or commercial viability.

Back to contents

Technical & Delivery Signals

The product was built with:

  • HTML5, CSS3, JavaScript for the web version;
  • GitHub Pages for hosting;
  • Python MVP using Gradio, pypdf, Pydantic structured data, automated tests, and optional OpenAI API integration;
  • Mobile-first design that works offline with synthetic demo data.

The author notes challenges in publishing using only an Android phone and plans to improve with Codex, GPT-5.6, PDF highlighting, OCR, multilingual support, and professional testing.

Inference: The technical approach is lightweight and web-based, with potential for AI integration. It is not yet production-ready or scalable.

Back to contents

Traction & Maturity Signals

The project is described as a hackathon prototype submitted to the OpenAI 2026 hackathon. It is not validated as a medical device and has no evidence of customer adoption, revenue, or usage metrics.

Not evidenced: No data on user engagement, retention, or real-world deployment.

Back to contents

Competitive Context

The description does not mention any competitors or similar tools in the healthcare information processing space. The author does not reference existing platforms or solutions that address the same patient needs.

Not evidenced: No competitive landscape analysis or differentiation strategy provided.

Back to contents

Key Risks & Red Flags

  • Unvalidated medical use case: The tool is not a validated medical device and is explicitly stated to not replace healthcare professionals.
  • Prototype stage only: It is described as a hackathon submission with no evidence of real-world testing or validation.
  • Limited technical maturity: The author notes challenges in publishing and plans for further development, including AI integration.
  • No commercial traction: No evidence of revenue, customers, or monetization.

Inference: The project is at a very early stage and carries significant risk due to the sensitivity of its intended use case without clinical validation.

Back to contents

Diligence Questions To Ask The Founders

  1. Has the prototype been tested with actual patients or healthcare professionals?
  2. What are the specific safety constraints implemented in the system, and how are they enforced?
  3. Are there any plans for regulatory compliance or medical device validation?
  4. How does the author intend to scale beyond a single-person hackathon project?
  5. What is the roadmap for integrating AI models like GPT-5.6, and what data will be used for training?

Back to contents

Investment/Partnership Verdict

The description presents ClaireSante as a conceptually promising but unproven prototype with no evidence of traction, revenue, or customer validation. It is positioned in a high-risk domain (healthcare) without clinical validation or commercialization strategy.

Confidence: Low — the project is described as a hackathon submission and lacks any verified business or technical progress beyond its initial design.

Verdict: Not ready for investment or partnership at this stage. Further evidence of testing, validation, and traction is required before considering deeper due diligence.

Back to contents

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.