Learnings

Experiments powered by AI.

I use AI to build and test digital products fast. These projects help me explore how design, automation, and language models can turn simple ideas into working tools.

I combine years of product design experience with AI coding tools to prototype, ship, test, and improve products quickly. Each project is a way to learn by building.

Coming soon

AI Assistant

Bentevi

Bentevi is an AI chat assistant designed to be simple to train and easy to embed on any website. A futute version of this Ai mode I have on my portfolio.

I use ChatGPT to plan the roadmap and product iterations, OpenAI Codex to built the POC and Anthropic Claude Code to build the prod version. The goal is to remove the complexity of traditional chatbots and agents, creating a lightweight and flexible AI assistant.

The project combines interface design, prompt design, token optimization, knowledge data, and user context to deliver high-quality AI conversations while minimizing hallucinations.

Coming soon

Translator

Rosetta Stone

Rosetta Stone is a translation tool designed to make web content more accessible across languages.

I use ChatGPT to plan the roadmap and iterations, OpenAI Codex and Anthropic Claude Code to implement the product. The goal is to allow blogs and websites to translate their content into multiple languages while preserving tone and meaning.

The project combines interface design, AI translation, SEO considerations, and content structure to ensure translated pages remain indexable by search engines while keeping the originality of the content.

Coming soon

Coffee Tracker

Pindorama

Pindorama is a tool to track the origin and characteristics of specialty coffee beans.

I use Gemini Deep Research to study the market, ChatGPT to plan the roadmap and iterations, OpenAI Codex to audit code and Anthropic Claude Code to build the product. The tool records information such as origin, altitude, climate, farm, and roaster.

It also helps users track tasting notes, roast dates, and brewing results. The project explores how structured data and AI can help organize personal habits and better understand the specialty coffee supply chain.