Azure, AI, Microsoft, and Everything In Between
Most LLM driven apps work well when the answer is obvious and short. They start to struggle when the answer is buried in a long document (context), split across sections, or only becomes clear after inspecting several nearby passages. That is exactly the kind of problem that RLM is designed for and this post explains … Read more
Multi-agent systems are exciting to build, and they’re also easy to get wrong. I’ve noticed a recurring pattern when developers start building with agents. The first agent is clear and focused. The second adds value. The third feels clever. By the fourth or fifth, the system still “works”, but no one knows why. Or what … Read more
In Part-1 of this series, I walked through building a Graph database from scratch, comparing traditional and LangChain-powered approaches to create knowledge graphs. I had a Neo4j database filled with entities and relationships, all extracted by GPT-4o running on Azure AI Foundry. But here’s the thing about Graph RAG – building the graph is just … Read more
Most AI applications today use RAG (Retrieval-Augmented Generation) to work with private data. The typical approach? Convert text into vectors and search for similar content. It works well, but it has a big limitation: it can’t see how different pieces of information connect to each other. Think about it like this – traditional RAG (sometimes … Read more
Background In the last month, Microsoft released the MSSQL MCP Server (Preview), a bridge that lets AI applications talk to SQL Server using Model Context Protocol. The announcement (see official post) sparked my curiosity, I wanted to test-drive natural-language querying against my own databases. While kicking the tires I discovered a limitation: the preview Node.js … Read more
For organizations leveraging OpenAI’s Agent SDK, one of the most important metrics to track is token usage. Tokens are the fundamental units of text processing in large language models, and they directly impact both performance and cost. This post explores how to track token usage in applications built with the OpenAI Agent SDK discusses the … Read more
Agents are everywhere these days, and yes it’s the new buzzword! Everyone is trying to build one, either to explore what’s possible or to solve real business problems. And with so many models and frameworks out there, it can get overwhelming. The OpenAI Agent SDK makes it easier to build agents, but not many developers … Read more
When I first started exploring AI-driven applications and experimenting with different emerging agent frameworks, one basic question consistently puzzled me: If we can implement the entire domain using a single agent, why complicate things by creating multiple agents to achieve same result? What additional value do multi-agent architectures offer? In this post, I’ll share insights … Read more
Context: A few weeks ago, an unexpected situation unfolded in one of the customer’s production environment. It all started when a member of their team decided to pull the trigger on “terraform destroy” command. Their intention was to remove a specific app registration from Azure AD that they deployed with a Terraform package, however, little … Read more
This short post is intended to share experiences while working on the following scenario: Azure function with managed identity Output bindings configured for service bus queue Although this may seem straightforward, we encountered some issues in making it work. The difficulties stemmed from the lack of clear documentation on this topic and the dependence on … Read more