Building dependable AI and full-stack systems for real business operations.
I build AI-driven backend systems, workflow automations, and agent-based services that handle real business operations with stability, traceability, and practical deployment in mind.
Rhanny Belle Urbis
AI Automation Engineer / Backend Engineer
My work focuses on dependable AI systems that collect, organize, analyze, and transform information into usable outputs for business teams. I design backends and automation pipelines that can process high volumes of data, avoid duplicate work, support long-running tasks, and remain maintainable in production.
Technical Skills
A focused snapshot of the tools and platforms used to deliver production automation, APIs, and AI systems.
Automation & Orchestration
Backend & APIs
Databases & Vector Storage
AI / LLM / Speech
Search & External Data
ETL, File & Data Processing
Data Analysis & Visualization
Dev Tools, Deployment & Integrations
Full-Stack Development
Featured AI/ML projects
A compact selection of apps and systems spanning AI interaction, retrieval, and workflow orchestration.
VoiceBuddy
Voice-focused AI app using OpenAI TTS for interactive speech generation and practical experimentation.
CarInsure Bot
Insurance assistant application built around retrieval and guided interaction patterns.
TripBites
Agent-driven travel and food exploration app using LangGraph + ReAct-style orchestration.
Engineering articles
Selected articles focused on retrieval design, backend reliability, practical architecture, and workflow automation.
Embeddings vs. Re-Ranking: How to Use Each
When embeddings are enough, when re-ranking is justified, and how to combine both in production retrieval pipelines.
How to Build a Fast & Reliable API for an ETL/Report Generation Agent
A practical pattern for keeping FastAPI thin while moving heavy ETL and report generation work off the request path.
Building Production-Ready Apps Without Over-Engineering
How to keep systems dependable and maintainable without adding unnecessary complexity too early.
Why Most Systems Don’t Have Real Error Handling
A production-minded look at failure handling, stability, and what real operational resilience requires.