I Built “What’s Inside?” for a Friend Who Wants to Know What She’s Actually Putting on Her Skin and Inside Her Body
What’s Inside? This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend . What I Built I built WHAT’S INSIDE? because of a friend of mine, A. She has always been quite particular about what she eats and what she uses on her skin and hair. If she is buying a shampoo, she will turn the bottle around and read the ingredients. If she is buying a snack, she will check the back…
This project, named "What's Inside?", was built for a friend who is very particular about the ingredients in the products she uses on her skin and hair. The creator, A, often consults ingredient labels and asks the builder if she doesn't understand certain components. The challenge with ingredient labels is that they tend to use complex terms that most people can't grasp without a background in chemistry or biology.
To address this issue, the developer created an application that allows users to take a photo of a product label, and the app breaks down the information into something more understandable. The app uses Gemma 4:12B locally through Ollama to read the label, identify the product, and extract its ingredients. These ingredients are then matched against a local knowledge base that provides information about their purpose, usage, scientific evidence, regulatory context, and uncertainties.
The developer made sure the application did not function as a "toxic chemicals" scanner, but instead aimed to provide balanced information. For instance, it doesn't immediately flag a complicated chemical name with a red warning sign. The application also allows users to specify their personal preferences, as not everyone is concerned about the same things. Some might be more worried about fragrance, while others might be concerned about allergens or food additives.
The application is designed to work locally, without depending on a cloud API. This decision was made to ensure the user's data stays private and secure. The user can upload a photo of a product's label, and the application will analyze it on the user's own machine. The UI is intentionally simple and minimal, designed to feel calm and understandable, much like the ingredient labels themselves.
The colors used in the interface serve a purpose, separating normal information from things worth paying attention to, evidence, and uncertainty.
The project started with a simple observation: a friend standing in a store aisle, trying to understand the ingredients on a shampoo bottle. The builder wanted to make this experience easier for her, and for others like her, by providing a clear understanding of what's in the products they use.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
