Luis OtavioLuisOtavio.

Problem

Tapnote, a Polish AI study app with 30,000+ 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, Node.js and AWS, 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

Enterprises such as Siemens Energy, Henkel and Essity needed a training platform where courses could be drafted automatically, with each organization's users and data strictly isolated.

What I built

• Architected the platform in Next.js, TypeScript and AWS, with LLM course generation and AI-assisted authoring tools.
• Owned multi-organization authentication and tenant isolation with Better Auth.
• Designed and shipped a peer review system so training creators receive structured feedback and ratings.
• Implemented ISO/IEC 27001 controls with Kertos, supporting the company's certification.

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 AI agent; 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 68 brigade documents with citations, plus voice notes in and out.
• Forked from my open-source AI Agent Boilerplate, with 2,300+ pytest and Vitest tests and Sentry monitoring.

Problem

Brazil-nut (castanha) collectors in northern Brazil sell with little visibility into what the harvest is fetching in other regions. I build the AI agent; 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

Travelers either book a fixed group tour or piece a day together from blogs and maps. TourLore is an AI tour guide and trip planner for iOS and Android: it writes a personal walking tour for any city, narrates each stop, works offline and answers photo questions mid-walk.

What I built

• Expo / React Native app with Expo Router, NativeWind, MapLibre maps, audio narration and offline mode, in a Turborepo monorepo with EAS builds.
• Backend: a Hono + tRPC API on Google Cloud Run, Zod contracts shared with the app, Drizzle on Neon PostgreSQL, Inngest background jobs, Sentry and GitHub Actions CI.
• An LLM tour-planning agent on the Vercel AI SDK and Gemini on Vertex AI, with tool calling, quality-gated by LLM-as-judge evals in Langfuse.
• The Next.js 16 landing site in 30 languages (next-intl), with a Resend waitlist.

Problem

When a change spans repos, you either restart in each repo and explain everything again, or let one AI agent edit a repo whose rules, hooks and conventions it never loaded.

What I built

• A Python CLI where a lead agent hands each repo's part of a change to a Claude Code or Antigravity agent working inside that repo, in its own git worktree, with that repo's rules loaded.
• Plan, review, execute: tasks are sized, strong models plan, the lead reviews each plan before any edit, and the same conversation executes on a cheaper model, switching models when a quota runs out.
• Every PR gets cross-agent reviews from Claude Code, Gemini (Antigravity) and GitHub Copilot, and every agent runs in a terminal pane you can watch and type into.

Problem

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

What I built

• Open-source WhatsApp assistant that brings LLMs from OpenAI, Anthropic, Google, Groq or OpenRouter into chats through LangChain and LangGraph, with web search, Google Routes, voice messages and group chats, plus Google Calendar on OpenAI models.
• Lead developer across 150+ commits.