Foundations¶
Three foundational mini-projects. General-purpose prompting and fine-tuning skills, practiced on health-science text but not tied to a specific clinical workflow. The on-ramp before Clinical Application and Basic Science projects. A frontend built by prompting an AI coding agent (Claude Code, Codex, or VS Code agent mode), talking to a backend built on open-source models and datasets.
| # | Project | Backend | Training? |
|---|---|---|---|
| 1 | Medical Term Definer | Local LLM via Ollama + prompt template | No |
| 2 | Health Literacy Rewriter | LLM prompting + textstat verification |
No |
| 3 | Mood Journal Sentiment Tracker | Fine-tuned emotion classifier | Yes |
Every project's backend runs on open-source models and datasets, and everything is inspectable locally. New to the tooling in general? Start with Software Engineering Practices for Data Science.