Protocolos AI

The description states that Protocolos AI is a web application that helps physicians:

• Manage patients and their clinical information
• Load and prepare clinical protocols
• Compare patients with protocol inclusion and exclusion criteria
• Detect missing or outdated information
• Generate an explained result for each patient and protocol
• Record the protocol version, sources, criteria, and reasoning used

The author notes it does not replace medical judgment but provides decision support, traceability, and organized initial review. During OpenAI Build Week, they added AI-generated patient briefings summarizing relevant information before consultations.

Evidence The project description explicitly lists these functions.

Inference The product appears to be a clinical workflow tool that leverages AI for protocol matching and patient data summarization.

The author positions Protocolos AI as:

• An AI-assisted tool for clinical protocol matching
• A system that maintains physician control over final decisions
• A solution that provides traceable criteria and explained results
• A decision support tool, not a replacement for medical judgment

Evidence The tagline "AI-assisted patient matching for clinical protocols with traceable criteria and explained results" and the project write-up's emphasis on keeping final decisions in physicians' hands.

Inference The positioning suggests an intent to address time-intensive protocol review processes while maintaining regulatory and ethical boundaries around AI use in healthcare.

The description states that Protocolos AI helps physicians:

• Manage patients and their clinical information
• Compare patients with protocol inclusion and exclusion criteria
• Generate explained results for each patient and protocol

Evidence The project write-up explicitly identifies physicians as the primary users.

Inference The target customer is likely medical professionals working in clinical settings who need to review patient data against complex protocols, such as researchers or clinicians involved in clinical trials or treatment guidelines.

Not evidenced.

Evidence No information provided about pricing models, monetization strategies, or business model assumptions.

Inference Given the hackathon nature and lack of commercial traction, there is no evidence of any established business model or pricing structure.

The application uses:

• React and TypeScript for frontend
• Supabase and PostgreSQL for authentication and data storage
• Supabase Edge Functions for backend processes
• Cloudflare Pages for deployment
• OpenAI Codex to analyze codebase, implement functionality, review changes, assist with testing
• GPT-5.6 to generate structured and traceable patient briefings from clinical information

Evidence The author's own write-up details these technologies.

Inference The stack suggests a modern, serverless approach using cloud infrastructure and AI APIs for both development and functionality.

Not evidenced.

Evidence No data on users, customers, revenue, or adoption is provided. The project was submitted to a hackathon competition and uses fictional patient data.

Inference There is no evidence of any traction, user base, or operational maturity beyond the initial prototype built during a single event.

Not evidenced.

Evidence No mention of competitors, market size, or competitive landscape in the description.

Inference The author does not reference existing tools or platforms addressing similar clinical protocol matching or decision support needs.

• Unverified claims: All features and functionality are self-reported without independent verification.
• No commercial traction: The project is a hackathon submission with no evidence of real-world usage or adoption.
• Limited scope: Only one team member (Fabian Mo) is listed, suggesting limited development capacity.
• Fictional data only: The demonstration uses fictional patient data, not real clinical information.
• AI dependency: Heavy reliance on AI tools for both development and functionality raises questions about scalability and control.

Evidence The description explicitly states this is a hackathon project with no verified users or revenue.

1. What specific clinical protocols are you targeting, and how do they differ from existing solutions?
2. How does the system handle edge cases where protocol criteria are ambiguous or conflicting?
3. Have you tested the system with actual physicians or medical professionals?
4. What is your plan for ensuring compliance with healthcare regulations (e.g., HIPAA)?
5. Can you demonstrate how the traceability and explained results work in practice?
6. How do you intend to scale beyond a single developer's capacity?