In 2003 via Microsoft Identity Integration Server (MIIS) Microsoft demoed Polyarchy Server a web visual over identity data showing intersecting relationship hierarchies, where clicking a datapoint flipped the […]
LLM calls are slow, costly, and non-deterministic, so a multi-agent app that crashes halfway through wastes time and money re-running everything. Dapr Workflow turns a set […]
I’ve been using Claude Code heavily across AI engineering work: RAG pipelines, .NET MCP servers, content automation, agentic workflows. The way I use it now looks […]
Almost a year ago I introduced EntraPulse a free, community cross platform desktop app that lets you query your Entra tenant, Microsoft Graph, and Microsoft Docs […]
I have spent a good while now building RAG pipelines across a number of engagements, mostly for documentation sites, and the gap between the tutorials and […]
As organizations continue to push workloads closer to where data is generated, edge computing is becoming a critical part of modern architectures. With the introduction of […]
Intro Foundry has had a messy start. The pivot from the classic hub/projects architecture to the “New” account model happened quickly and feature parity still isn’t […]
I recently had a situation where a continuous Azure WebJob running a documentation crawler stopped overnight. The crawler formed part of an ingestion sequence in a […]
LLMs are frozen at training time, so they return confident answers that may already be out of date. This free, self-paced Dapr University track shows you […]
In this blog, I run through a debug session that took me a while to diagnose. Documents in a production RAG pipeline were intermittently failing to […]
A production RAG-powered documentation chatbot started throwing intermittent “Server Error” responses. No obvious pattern, no reliable repro, and the first sign of trouble was an automated […]