What I built
A medical training organization needed an AI assistant that helps students and developers learn FHIR (Fast Healthcare Interoperability Resources) through hands‑on coding practice. The AI had to provide instant, accurate feedback on code based strictly on official training materials – no generic internet knowledge.
I built HealthCoach AI to solve this exactly.
Key features
- Upload FHIR guidelines (PDF, DOCX, TXT) – the AI answers only from those documents
- Coding practice module: users write Python code to manipulate FHIR JSON (e.g., calculate patient age from a Patient resource)
- Real‑time AI feedback on code correctness, style, and FHIR best practices
- Multilingual support (English, French, Spanish)
- Female AI voice introduction that explains the platform
- Fully self‑hosted – the client runs it on their own infrastructure
Tech stack
- Python
- Streamlit
- Groq Llama 3.1 (RAG)
- edge‑tts for voice
- FHIR JSON data models
Live demo
https://healthcoach-ai-fhir-training-uzdeefhyupvfjkywurau6w.streamlit.app/
What we do at GlobalInternet.py
We provide tailored software solutions that connect the global market with local expertise. We build custom AI‑powered applications, business tools, and automation systems – delivered fast with full source code.
Contact us
Phone: (509) 4738 5663
Email: deslandes78@gmail.com
Website: https://globalinternetsitepy-abh7v6tnmskxxnuplrdcgk.streamlit.app/
What's next
I am adding more FHIR practice problems and a progress dashboard for students to track their learning.
Feedback welcome
Try the live demo, write some code, and test the AI feedback. I would love to hear your suggestions or feature requests. Comment below or reach out via my website.
Top comments (0)