Medipok

The description states that Medipok is a clinical simulation game designed for medical professionals and students. It allows users to:

• Encounter AI patients with authored clinical conditions.
• Conduct examinations, request tests, interpret results.
• Make treatment decisions and submit cases for evaluation.
• Receive structured feedback and rewards based on their choices.

The experience is built in Unity, using C# for the front-end, and integrates a case engine written in TypeScript with Zod for validation. Backend services use Nakama and PostgreSQL. AI is used primarily for natural conversation but does not override deterministic clinical facts.

The system currently supports ten authored cases, with one fully playable demo case included in the submission.

Note: This is a self-reported product description. No independent verification of functionality or user experience exists.

The author positions Medipok as:

• A clinical training game that shifts from passive learning (e.g., textbooks) to active engagement.
• A way to simulate real-world patient encounters in an immersive environment.
• An alternative to traditional question banks and isolated testing.

It claims to bridge the gap between academic knowledge and clinical practice by allowing learners to "enter a living game world."

This is a claim about intent and positioning, not proof of traction or adoption.

The author states that Medipok targets:

• Healthcare professionals
• Medical students

These are described as users who want to learn through treating patients rather than answering isolated questions.

No further segmentation or customer data is provided. The description does not indicate whether the target includes educators, institutions, or other stakeholders.

There is no evidence of a business model or pricing structure in the project description.

The author mentions:

• The tool was built for a hackathon.
• Future features include multiplayer cases and procedural simulations.
• No mention of monetization, licensing, subscriptions, or sales channels.

Not evidenced.

Key technical elements mentioned:

• Built with Unity, C#
• Backend uses Nakama, PostgreSQL
• Case engine built in TypeScript and validated using Zod
• AI integration via Codex and GPT-5.6
• Supports structured patient interaction, deterministic clinical truths, and conversational AI

The author notes:

• Separation of dialogue generation from authoritative case state.
• Use of AI for conversation while maintaining medical accuracy.

These are self-reported technical details; no evidence of scalability, performance, or deployment in production.

There is no evidence of traction, revenue, or customer adoption beyond the author’s own account. The project:

• Is a hackathon submission.
• Contains only one demo case out of ten authored cases.
• Has no mention of users, usage metrics, or feedback loops.

Not evidenced.

The description does not reference any competitors or market positioning relative to existing tools in medical education or simulation gaming. No comparison with platforms like Osler, CaseManager, or other clinical training systems is made.

Not evidenced.

• Unverified claims: All statements are self-reported and unverified.
• Early-stage prototype: Built for a hackathon; no evidence of product-market fit or user testing.
• No business model: No indication of how the tool would be monetized or scaled.
• Single founder: Team size is listed as one person, which may limit execution capacity.
• AI dependency risk: Reliance on AI models (Codex, GPT) for development raises concerns about availability and control.

These are inferences based on limited evidence.

1. What is the source of the clinical content used in the authored cases?
2. How does the system ensure that AI responses remain medically accurate without inventing facts?
3. Are there any plans to integrate real-world data or collaborate with medical institutions?
4. Has the prototype been tested with actual medical students or professionals?
5. What is the long-term vision for scaling beyond a single-player, demo-style experience?
6. How does the team plan to monetize this product if it moves beyond a hackathon project?