ai-assisted
Why AI-era operating models require better data product ownership and lineage
Why AI-era operating models require better data product ownership and lineage
Artificial intelligence and machine learning
ai-assisted
Why AI-era operating models require better data product ownership and lineage
ai-assisted
Three full-stack data platforms in a weekend: what Fabric and Azure AI Foundry enable for rapid delivery
ai-assisted
From experimentation to operations: what weekend-built AI data platforms teach us about production readiness
ai-assisted
From Data Movement to Decision Velocity: Why Faster Python Reads Matter for Copilot and AI Analytics
ai-assisted
Building Copilot-style experiences in Python with the Microsoft Teams SDK
ai-assisted
How Microsoft Agent 365 changes enterprise AI governance
ai-assisted
Why Most Enterprise AI Projects Stop at the Demo
ai-assisted
Build an Enterprise ready 2nd Brain on Azure Foundry + Cosmos DB
Azure
Processing hundreds of multi-page PDF forms manually is exactly the kind of repetitive work that AI should handle. I built an automated document processing pipeline on Azure that splits PDFs, extracts structured data using AI, and stores results — all triggered by a simple file upload. The Problem Imagine receiving a
AI/ML
What if you could query databases, search documents, and run multi-tool AI workflows — all without a single byte leaving your machine? That's exactly what I built with the Local LLM Universal Research Agent. The Problem Most AI agent frameworks assume cloud APIs. That's fine for many
AI/ML
How I run 34 large language models locally using Ollama on consumer GPUs, with practical tips on model selection, performance, and integration.