Stack
Learning by pointing your camera
The app lets you point your camera at something in the real world, an apple, a chair, a street sign, and hear and read its name in the language you are learning. It is a small idea with a surprisingly motivating effect, because it ties new words to real things in front of you instead of a flashcard.
Three AI steps in a chain
Under the hood it is a chain of three models, each feeding the next. Vision identifies the object, translation turns the word into the target language, and text-to-speech reads it aloud with a decent accent. Each step is simple on its own; the product is the chain.
- Image to text: a vision model names what the camera sees.
- Text to text: a translation step converts the word into the target language.
- Text to audio: a speech model pronounces it, so you learn how it actually sounds.
What chains teach you about errors
The hard lesson of chaining models is that errors multiply. If each step is 90 percent reliable, three steps in a row are not 90 percent reliable, they compound, and a wrong word identification at the start poisons everything after it. So the real work was making each step fail gracefully and visibly: if vision is unsure what the object is, the app says so rather than confidently teaching you the wrong word. Building this changed how I think about multi-step AI products. The magic is in the chain, but the reliability is in how honestly each link admits when it is unsure, so a small early mistake does not silently become a confident wrong answer at the end.
Lessons learned
- In a chain of models, errors compound. Three reliable steps in a row are less reliable than any one alone.
- Make each step fail visibly. A confident wrong answer early poisons every step that follows.
- The product is the chain, but the trust is in how honestly each link admits uncertainty.
- Tying new information to real-world objects is a genuinely strong hook. Use the medium, do not fight it.