Luis OtavioLuisOtavio.

Problem

Poland's #1 AI tutor app, with 30,000+ active subscribers, lived on mobile. Students needed the same tutor on the web.

What I built

• Architected the full-stack web app with Next.js, React, TypeScript, Tailwind CSS and Node.js, reaching feature parity with the native mobile app.
• Engineered AI tutoring features with LLMs and RAG on a PostgreSQL / Supabase backend for context-aware homework help and personalized study assistance.

Problem

Companies needed a training platform where courses could be created automatically, with each organization's users and data strictly isolated.

What I built

• Architected the platform in Next.js, integrating automated course creation with LLM-driven content generation.
• Owned the end-to-end multi-organization authentication system with Better Auth for secure tenant isolation.
• Designed and shipped a peer review system so training creators receive structured feedback and ratings.

Problem

Volunteer fire brigades in central Brazil coordinate in group chats, far from the Caminho do Fogo platform where alerts, fires and field actions are recorded. I build the bot; Terra Krya brings it to the brigades.

What I built

• WhatsApp and Telegram agent with one shared memory: brigade members sign in from the chat, then report alerts and fires with a location pin and photos, each write confirmed before it is saved.
• Fire status updates, field actions, area notifications and the INPE fire-risk forecast up to three days ahead, all by conversation.
• RAG over brigade documents with citations, plus voice notes in and out.

Problem

Brazil-nut (castanha) collectors in northern Brazil sell with little visibility into what the harvest is fetching in other regions. I build the bot; Terra Krya brings it to the communities.

What I built

• WhatsApp agent on the IE Sociobio platform: producers log prices just by talking, and compare their region with others.
• A weekly regional recap posted to each group, with prices, harvest counters and phase, rewritten or rescheduled by asking the bot.
• The Caderno da Safra harvest survey answered by conversation, plus operator broadcasts paced to stay clear of spam detection.

Problem

Bring context-aware LLM answers into the chat app people already use every day.

What I built

• Open-source WhatsApp chatbot that connects LLMs, including Bing AI, to WhatsApp conversations.

Problem

LangChain.js agents had no native way to plan routes, so travel and logistics agents had to hand-roll Google Maps calls.

What I built

• Contributed the Google Routes Tool to LangChain.js: agents can ask for routes, travel times and distances through Google's Routes API.
• Shipped with docs and tests, reviewed and merged by the LangChain maintainers.