Adrian Zambrana
Acquarts
Full Stack LLM Developer Analyst at Accenture, Applied AI & Product Engineer | Data Scientist | Machine Learning | Master’s in AI
Languages
Repos
24
Stars
1
Forks
0
Top Language
Python
Loading contributions...
Top Repositories
Interactive web application for musical genre analysis and artist comparison using the Spotify API.
Multi-agent system that automates the creation of professional commercial and technical proposals using A2A (Agent-to-Agent) orchestration and MCP (Model Context Protocol).
An end-to-end Machine Learning application that predicts developer stress levels based on work patterns, habits, and environmental factors. Built with production-grade practices including CI/CD pipelines, containerization, automated testing, and cloud deployment.
A collection of AI agents built with Google ADK, LangChain, and modern agentic tools.
An AI-powered video game assistant built with Google Agent Development Kit (ADK) and Gemini 2.5 Flash. Features a multi-agent architecture with specialized sub-agents for YouTube video search, web search, and URL verification.
Repositories
24Interactive web application for musical genre analysis and artist comparison using the Spotify API.
Multi-agent system that automates the creation of professional commercial and technical proposals using A2A (Agent-to-Agent) orchestration and MCP (Model Context Protocol).
An end-to-end Machine Learning application that predicts developer stress levels based on work patterns, habits, and environmental factors. Built with production-grade practices including CI/CD pipelines, containerization, automated testing, and cloud deployment.
No description provided.
A collection of AI agents built with Google ADK, LangChain, and modern agentic tools.
An AI-powered video game assistant built with Google Agent Development Kit (ADK) and Gemini 2.5 Flash. Features a multi-agent architecture with specialized sub-agents for YouTube video search, web search, and URL verification.
An intelligent virtual receptionist for Camping La Rosaleda, built with Google ADK (Agent Development Kit) and Vertex AI RAG Engine.
End-to-end Machine Learning system for flight price prediction with REST API, web interface, CI/CD pipeline, and AWS deployment
Web application to predict medical insurance costs using Machine Learning, deployed on Google Cloud Run.
Production-ready deployment solution for Google ADK Agents to Vertex AI Agent Engine. Fixes the critical CLI bug (ModuleNotFoundError: agent_engine_app) with programmatic deployment templates. Includes comprehensive guide.
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
The platform integrates multiple generative artificial intelligence models to create a complete solution for marketing, design and content creation teams. The project solves the business need to generate high-quality visual and textual content efficiently
Development of Data Science solutions applied to real problems, combining exploratory data analysis, advanced visualization and Machine Learning model implementation.
Funndication DJ Bookings is a web application that facilitates the hiring of DJs. The system uses artificial intelligence (OpenAI) to maintain natural conversations with clients, manage artist availability and automatically calculate prices based on location and event duration.
An interactive web application built with Streamlit that uses YOLOv8 to automatically detect objects and people in videos.
An intelligent travel planning system that uses OpenAI GPT-4o, RAG (Retrieval-Augmented Generation) and advanced Prompt Engineering techniques to generate high-quality personalized itineraries for any Spanish city.
Un sistema inteligente de recomendación de películas y series de Netflix utilizando Machine Learning y Streamlit.
Full Machine Learning project to predict the median house value (median_house_value) in California districts. It includes exploratory data analysis (EDA), comparative model training, a REST API built with FastAPI, and a Streamlit frontend for performing both individual and batch (CSV) predictions.
An advanced web application built with Streamlit and YOLOv8 that detects, tracks and analyzes the movement of vehicles and people in videos. Ideal for traffic analysis, security, urban monitoring and behavioral studies.
End-to-end Machine Learning project for predicting customer churn in a telecommunications company. Built following industry best practices and MLOps principles.
Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.
This repository contains my Data Analytics projects, exercises, and experiments as I build my expertise in this field. Expect a blend of technical analysis with a creative mindset shaped by years of visual storytelling in games.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models
Generates concept art for video games using Claude (prompts) + FLUX (images via fal.ai)