This is a submission for the Built with Google Gemini: Writing Challenge
What I Built with Google Gemini
I built a full-stack AI-powered pharmacy management system that helps pharmacies prevent losses from expired medicines and stock shortages. The idea came from a real conversation with a pharmacy employee who told me she was personally responsible for any medicines that expired without being reported in time. That problem needed a solution.
Working alongside Gemini as a coding partner, my process started with an idea — then I asked the AI what the best programming language and stack would be for this specific project. After evaluating the suggestions, I made the final decision myself: FastAPI for the backend, React with TypeScript for the frontend, and Groq's free AI API for the intelligent features.
Gemini helped me write the code, but the process was far from automatic. I encountered indentation errors, broken endpoints, deprecated model names and missing imports. I debugged using tools like Chrome DevTools, Postman and careful error reading. The first design didn't match my vision so I pushed for a complete redesign. Every broken point had to be identified, understood and fixed.
What I learned is that in this era of AI tools, the most valuable skills a software engineer can have are not just technical knowledge — they are the ability to generate real ideas from real observations, and the ability to resolve conflicts by combining tools like Gemini, Postman and browser debugging with their own programming knowledge and creative thinking.
AI can write code. It cannot walk into a pharmacy, have a conversation, and turn that moment into a solution. That part was mine.
Demo
What I Learned
Technical skills:
Working on this project taught me full-stack development end to end — building REST APIs with FastAPI, building interactive UIs with React and TypeScript, managing data with SQLite and SQLAlchemy, securing an application with JWT authentication and role-based access, and integrating third party AI APIs.
Soft skills:
I learned how to work with AI as a tool rather than a shortcut. The process of reading error messages, understanding what went wrong, and deciding how to fix it built more confidence than any tutorial could. Persistence matters more than perfection.
Unexpected lesson:
The most important thing I took away is that ideas are still irreplaceable. I walked into a pharmacy, had a real conversation, identified a real problem and built a solution for it. No AI prompted me to do that. In a world where AI can generate code in seconds, the engineers who will stand out are the ones who bring the problems worth solving.
Google Gemini Feedback
What worked well:
Gemini was genuinely helpful for scaffolding code quickly, suggesting tech stacks, explaining concepts and helping debug errors when given the right context. The speed of going from idea to working prototype was impressive. For someone learning while building, having an AI that could explain why something works — not just what to write — was valuable.
Where I needed more support:
There were moments where Gemini suggested deprecated libraries or model names that no longer worked, which required extra research to resolve. Sometimes the generated code had structural issues like incorrect indentation or logic placed outside the right scope that were not immediately obvious.
The biggest friction was that AI responses assume a perfect environment — they don't always account for version conflicts, operating system differences or local setup issues. Those gaps required combining Gemini with other tools like Chrome DevTools and Postman to fully resolve.
Overall:
AI is an incredibly powerful coding partner when you bring the ideas, the judgment and the debugging skills. That combination is where the real value is.
#react, #Python, #full-stack
Thanks for participating!
Top comments (0)