Arepa.AIFounder & AI Engineer
Arepa.AI: Agentic AI Platform for Spanish-Speaking SMBs
Building LangGraph agents with RAG pipelines and voice interfaces for small businesses across Latin America.
- LangGraph
- RAG
- Python
- AWS
- Terraform
- Voice AI
Building LangGraph agents with RAG pipelines and voice interfaces for small businesses across Latin America.
I applied the same engineering rigor behind my voice agent to a 50-year-old family car wash in Cabimas, Venezuela. An AI dirt scanner that roasts your car in maracucho dialect, a membership model built on unit economics, and a digital presence created almost entirely with AI tools, for a business that had never had a website.
Small businesses in Latin America operate in a different reality than Silicon Valley startups. They don't have engineering teams. They don't have data infrastructure. They often don't have a website. But they have the same operational problems that AI can solve: answering customer questions, scheduling appointments, managing inventory, and following up on leads.
Arepa.AI is the platform I'm building to bridge that gap. The name is a nod to my Venezuelan roots - the arepa is the most universal food in the culture, and this project aims to make AI equally accessible.
Most AI tooling assumes English-first, enterprise-scale, and technical users. That leaves out millions of small businesses across Latin America who could benefit from automation but can't afford a $200K consulting engagement or navigate English-language documentation.
The specific gaps I'm targeting:
| Layer | Technology | Rationale | |---|---|---| | Agent Orchestration | LangGraph | State machines over chains - business workflows map naturally to state graphs | | Observability | LangSmith | Full trace visibility for debugging Spanish-language edge cases | | Vector Store | Supabase (pgvector) | Isolated namespace per business, multilingual embedding support | | Embeddings | Multilingual model | Preserves semantic accuracy across Spanish dialects | | Infrastructure | AWS (Lambda, S3, CloudWatch) | Serverless execution with per-business cost isolation | | IaC | Terraform | All infrastructure as code from day one | | Voice | LiveKit | Same stack as celestino.ai |
I chose LangGraph over raw LangChain or custom orchestration for three reasons:
The retrieval layer ingests business-specific content: menus, service lists, pricing, FAQs, and operating hours. Each business gets an isolated vector namespace in Supabase (pgvector).
Key design choices:
This project is in active development. What's working:
What's next:
I'm building Arepa.AI because it sits at the intersection of everything I've learned: production AI engineering from Eventbrite, data pipeline design from FlowWest, and product thinking from building celestino.ai. It's also the hardest version of the problem - making AI work reliably in a language and market that most tooling ignores.
This isn't a demo. It's a business I'm building in public, with the same engineering rigor I'd bring to any production system.
If you're building AI for non-English markets, multilingual SMB automation, or production RAG pipelines with real cost constraints, the architecture decisions documented here apply directly. The same systems thinking - unit economics, multilingual grounding, multi-tenant infrastructure - transfers to any domain.
Explore AI Consulting Services or submit an inquiry - I'll respond within one business day.