Medibot AI: Synthetic Test Scenarios and Validation Artifacts (Underlying Data)

This repository contains the underlying data supporting the software tool Medibot AI , a web-based intelligent system that integrates the Gemini API to generate structured informational over-the-counter (OTC) medication guidance from user-reported symptoms. To ensure transparency and reproducibility, the dataset provides a curated set of synthetic test scenarios designed to evaluate diverse symptom profiles and safety-related conditions, including pediatric cases, pregnancy, chronic diseases, and clinical red flags. All cases are fully synthetic and do not contain real patient information. Contents* Synthetic test scenarios (synthetic_test_scenarios.json): 30 structured cases (MedicalInput) representing diverse risk contexts.* Sample outputs (sample_outputs.json): example responses aligned with the Medibot AI output structure (MedicalResponse).* Schema definitions (schema.json): JSON schema describing both input and output formats. Privacy and ethics No real clinical data were collected or used. The dataset contains no patient-identifiable information and is intended exclusively for reproducibility, validation, and educational purposes. License This dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.