#data-engineering

Operational database for AI agents , causal lineage (why()), semantic memory, live dashboards, MCP + Python/TypeScript SDK. Self-host or use db.zizka.ai.

AI-powered healthcare claims analytics using Python, SQL, and Tableau

A production-grade multi-agent ETL system orchestrated by Apache Airflow. Features real-time Kafka streaming, Dead Letter Queue routing, BigQuery integration, a FastAPI control layer, and a React-based "Cosmos" UI for live pipeline topology and quarantine management.

End-to-End Real-time Zomato Data Engineering Pipeline built using Apache Kafka, PySpark, AWS S3, Delta Lake, and OpenAI API for review sentiment analysis.

A bounded SQL-on-files CLI for coding agents. SQL in, files out.

DroneRF is an open-source PyTorch-based 1D CNN system that detects and classifies UAV RF transmissions directly from raw IQ signal samples.

Local-first data reliability agent with dataset profiling, typed findings, quality scoring, and report traces.

Pipeline ETL météo orchestré avec Apache Airflow et Docker

Enterprise Agentic AI Platform for autonomous pipeline monitoring, root cause analysis, incident retrieval, data quality validation, and self-healing workflow orchestration using LangGraph, FAISS, Vector Search, and Python.

An Airflow-orchestrated ETL demo: extract, transform, and load daily sales data through a simple, testable task pipeline.

Personal AI Data Engineering lab, portfolio and publishing platform built with FastAPI, PostgreSQL and modern engineering practices.

The on-call data team that gets smarter every night. Claude agents on DataHub: incidents resolved, postmortems remembered in the graph itself.

Live fantasy-cricket auction room with a data-driven player valuation engine and an AI bid advisor

Lint the documentation & metadata quality of VGI (Vector Gateway Interface) data workers — descriptions, column comments, tags, and example queries — with a quality score, per-version baselines, and agent-friendly output.

“Job Market Radar: a data pipeline for job post collection + governed analytics API + Agent to analyze job postings.”

Área de atendimento de uma distribuidora de energia no Databricks: medalhão, dashboard e copiloto conversacional, construídos com Claude Code e as skills do AI Dev Kit.

Multi-cloud market intelligence on AWS / Azure / GCP - live GPU pricing tracker, 2016-2026 market history from SEC filings, SQL star schema, interactive dashboards