Designed and developed IAnversicERP, a multi-module enterprise management system tailored to business workflows and Ecuadorian regulatory requirements. The platform integrates Human Resources, Attendance, Budget Management, Procurement, Electronic Signatures, and Taxation. The project combines backend and frontend development, module integration, automated testing, and validation to deliver a maintainable system for managing business operations in a unified platform.
0
12
I built IAnversic EVAL, a platform focused on evaluating and improving the reliability of AI applications, particularly LLM-powered systems and Retrieval-Augmented Generation (RAG) pipelines.
The project addresses a key challenge in AI engineering: moving beyond subjective assessments of model responses toward systematic, repeatable evaluation. It is designed to help developers assess answer quality, factual grounding, and retrieval performance, identify failure cases, and validate changes before deploying them.
Project outcomes and capabilities:
Designed a dedicated platform for evaluating LLM applications and RAG workflows.
Focused on assessing response quality and the relationship between generated answers and retrieved context.
Established a foundation for repeatable evaluations to compare configurations and identify regressions.
Connected evaluation to practical AI engineering workflows, supporting evidence-based decisions about prompts, retrieval strategies, and model selection.
IAnversic EVAL is part of the broader IAnversic ecosystem, complementing IAnversic RAG with an evaluation-focused approach to building more reliable, measurable, and production-ready AI systems.
0
15
I built IAnversic RAG, a privacy-focused knowledge retrieval system that enables organizations to search internal documents and obtain AI-generated answers grounded in verifiable sources.
The project delivers a full-stack RAG application built with FastAPI, PostgreSQL, pgvector, Ollama, and Next.js. It combines hybrid semantic and full-text search, optional reranking, source citations, and database-level permission filtering to support secure, context-aware retrieval.
Concrete results:
Implemented an end-to-end document ingestion and retrieval pipeline with source-grounded answers and citations.
Integrated PostgreSQL full-text search and vector similarity search using pgvector and HNSW indexing.
Implemented organization-level data isolation, role-based access controls, and API key management.
Enabled configurable local LLMs and embedding models, supporting self-hosted deployments and greater control over sensitive data.
Packaged the application into Docker services for the database, migrations, API, background worker, model runtime, and web interface.
The result is a modular, self-hostable RAG platform designed to help businesses make internal knowledge more accessible while maintaining control over their data and infrastructure.
0
21