Designing an AI-powered copilot that helps pharmacists prevent drug interaction errors before they reach patients. A project bridging pharmaceutical knowledge with AI/ML-driven design thinking.
Every day, Indian pharmacists process hundreds of prescriptions manually with minimal digital support, risking patient safety.
Manual checking of drug combinations is time-consuming and error-prone. Critical interactions like Warfarin + Aspirin often go undetected.
Illegible handwriting leads to dispensing errors. No OCR or digital parsing exists in most pharmacy workflows in India.
Patients often speak regional languages. Pharmacists struggle to counsel effectively without language-matched scripts.
† Sources: CDSCO Pharmacovigilance Programme of India Annual Report 2023; IMS Health India Prescription Audit 2022.
Contextual research with pharmacists and a review of pharmacy workflows in Pune, combined with structured drug interaction data from DrugBank India, revealed critical friction points.
| Feature | Others | RxCopilot |
|---|---|---|
| Drug Interaction Check | Partial | Full |
| OCR Prescription Scan | No | Yes |
| Regional Language Scripts | No | Yes (12) |
| Doctor Query System | No | Yes |
| EMR Integration | Partial | Yes |
| Audit and Reports | No | Yes |
Mapping the end-to-end pharmacist workflow revealed where RxCopilot adds the most value.
Patient arrives with prescription
Verify drug combinations manually
Identify critical interactions
Contact prescriber for confirmation
Hand over medication safely
| Section | Screen | Primary Action | User Need |
|---|---|---|---|
| Onboarding | Login + Language Selection | Sign In | Secure access, language preference |
| Workspace | Dashboard | View Queue and Alerts | Daily overview, critical flags |
| Workspace | Prescription Queue | Review prescriptions | Prioritized work list |
| Workspace | Scan Prescription | OCR scan and parse | Digital capture from paper |
| Workspace | Scan Result | Review and Confirm | Verify extracted data |
| Workspace | Drug Interaction Alert | Override or Refuse | Informed decision making |
| Workspace | Patient History | View timeline | Past medications and allergies |
| Workspace | Doctor Queries | Send and track queries | Prescription clarification |
| Workspace | Counseling Guide | Follow script | Patient counseling support |
| Analytics | AI Performance | View metrics | Accuracy and impact tracking |
| Analytics | Reports | Export data | Compliance and audit |
| Settings | Profile and Preferences | Configure | Personal and language settings |
Before landing on the current direction, three early concepts were explored and discarded. Showing what did not work is as important as showing what did.
Before any visual design, I worked through layout logic and structural alternatives in Figma lo-fi. Four decisions shaped the final layout the most.
Every key decision had an alternative considered and a reason chosen. Here are the 5 screens where design thinking mattered most.
Walk through a real prescription scenario end-to-end. Start from the Login screen, scan Priya Sharma's prescription, review the Warfarin + Aspirin critical alert, query the doctor, and complete the counseling session in Marathi. No login required.
This is an academic PGP project. The prototype was tested with real pharmacists using moderated sessions on the Figma clickable prototype and the standalone HTML build. No live system was deployed.
| Participant | Background | Tasks Done |
|---|---|---|
| P1 | Hospital pharmacist, 6 yrs exp | 6 / 6 |
| P2 | Retail pharmacy, 3 yrs exp | 5 / 6 |
| P3 | Clinical pharmacist, 4 yrs exp | 6 / 6 |
| P4 | Pharmacy student intern, 1 yr exp | 4 / 6 |
| P5 | Hospital pharmacist, 8 yrs exp | 6 / 6 |
Two of the most significant design changes, shown with the final screens side by side.
Key design decisions driven by user testing and feedback.
A medical tool must account for failure. These are the edge cases considered and how the design responds.
These outcomes are based on three sources: usability testing with 5 pharmacists in Pune, simulation using 200 sample prescriptions from the DrugBank India dataset (160 training, 40 held-out test), and expert review by a B.Pharm faculty member. This is a design prototype - not a deployed product.