I build AI products that solve real problems
From AI-powered financial analysis to real-time language learning: three shipped products with real users and real payments, built end to end.
Projects
AI applications built from problem to production.
Spralingua
AI language learning platform that delivers personalized lessons, real-time grammar correction, and natural conversation practice in 4 languages.
TubeText
AI-powered YouTube transcript extraction with LLM summaries, real-time streaming translation, and audio transcription — deployed as a production SaaS.
AgoraFinancials
Multi-LLM stock evaluation engine that orchestrates 9 AI models to analyze SEC filings, debate disagreements, and produce bias-reduced financial ratings.
The Problem
Language learners plateau because generic apps lack personalized feedback and real conversational practice. Existing tools treat every learner the same, ignoring proficiency gaps and native language interference patterns.
The Approach
Built a full-stack platform using Claude's language understanding to generate adaptive lessons, provide contextual grammar corrections, and simulate natural conversations. Multi-agent architecture with specialized agents for vocabulary, grammar, and conversation.
The Result
A production application serving users across 4 languages (Spanish, German, Portuguese, English) with real-time speech-to-text, text-to-speech, and intelligent lesson progression. Sub-2-second conversation loop. Deployed on Railway with PostgreSQL persistence.
Key Decisions
Chose Flask over Django for faster iteration. Used Minimax TTS for natural-sounding multilingual speech. Implemented session-based learning to track progress without requiring accounts. Prioritized conversation quality over feature breadth.
The Problem
YouTube holds massive knowledge but extracting insights from long videos is inefficient. No tool combined transcript extraction, AI summarization, and multilingual translation in one pipeline.
The Approach
Async FastAPI backend orchestrating multiple AI services: Deepgram Nova-3 for audio-to-text, LangChain + OpenAI GPT-4 mini for structured summaries, Cerebras Llama-3.3-70b for real-time streaming translation via SSE. PostgreSQL with async SQLAlchemy and Alembic migrations. Dockerized and deployed on Railway.
The Result
Production app at tubetext.app. Transcripts in seconds, AI-generated summaries, streamed translations (Spanish, French, German, Portuguese), and PDF export. Google OAuth + Stripe integration for billing.
Key Decisions
FastAPI for async-first performance. LangChain agents with YAML-driven prompts for maintainable AI pipelines. SSE streaming for real-time translation feedback. Deepgram over Whisper for production reliability. Docker + Railway for reproducible deployment.
The Problem
Stock analysis is drowning in information. LLMs can condense SEC filings into narratives, but a single model can hallucinate numbers, cherry-pick data, and bias its conclusions. No existing tool cross-validates AI-generated financial analysis.
The Approach
Built the Pythagoras Method: multiple LLMs independently evaluate 8 financial metrics, their ratings are harmonized, and conflicts trigger structured multi-round debates until consensus. Two-tier model architecture (fast for numbers, deep for RAG-powered qualitative reasoning) with OpenRouter as unified gateway.
The Result
Production platform at agorafinancials.com. 9 LLMs across 5 providers running in parallel, SEC filing RAG with pgvector, PDF report generation with scoring, Stripe billing with token economy, and watchlist with live scores.
Key Decisions
OpenRouter for unified multi-provider billing. LangChain create_agent with retrieval tools for deep-tier models. pgvector over Pinecone for simpler single-database infra. Sliding-window debate compression to keep token costs flat across rounds.
Luis Zermeno
I started in recruitment - four years sourcing engineers and closing roles across DACH and EMEA for companies like LucaNet and Volocopter. That taught me how software teams work, what problems they actually face, and what "production-ready" means beyond the buzzword. Then I made the leap.
Now I build AI applications end to end. I've shipped three production products with real users and real payments - a multi-LLM financial analysis platform, a YouTube AI transcription SaaS, and a voice-powered language learning app. My stack runs from LangChain agents and RAG pipelines to Stripe billing and Docker deployment.