Agentic Analytics: Supercharging Ad-hoc Analytics with Local LLMs

Introduction Nowadays, much of the online commentary related to Generative AI is focussed on Automated code Generation and rightly so. But Lets look at alternate use case of it. Traditionally, Business Intelligence (BI) relies on custom-built dashboards and reports that query a data warehouse. This often requires heavy intervention from engineering teams to analyze requirements, develop artifacts, and maintain them over time. Imagine your data warehouse is built on a SQL-based DBMS with a custom web interface for analytics. Even with this setup, typical challenges remain: ...

May 3, 2026 · 7 min · Sachin Sunkle

Why use Dapr (Distributed Application Runtime)?

Introduction This article explores various ways in which Dapr helps with development and operations of distributed applications. If you build software today, you are likely building a distributed system. Whether it’s two services talking or a monolith calling a lambda, you have crossed the process boundary. Distributed applications are software systems that consist of multiple components or modules running independently over network. These components work together to achieve a common goal while communicating and coordinating their actions across the network. ...

December 6, 2025 · 10 min · Sachin Sunkle

Notes on Excellent AI Agent Architecture via A2A/MCP by Jeffrey Richter

Introduction This article compiles my notes on an excellent architectural deep-dive by Jeffrey Richter. He outlines how to architect robust AI Agents using Google’s Agent-to-Agent (A2A) protocol for coordination and Anthropic’s Model Context Protocol (MCP) for tool integration. It is a must-read for anyone moving beyond simple chatbots to complex agentic workflows. You can read the original article here. ...

December 2, 2025 · 3 min · Sachin Sunkle