How to Move from Logic Apps to Autonomous AI Agents on Azure, Safely
TL;DR: Most teams want to move from workflows that call an agent to agents that run the work, but they still need to audit and check every outcome. The way...
Category: AI Engineering
Copilot Studio Harnesses Explained: The Runtime Choice That Decides What Your Agent Can Actually Do
Azure AI · Copilot Studio · LLMs TL;DR - Microsoft has taken the GitHub Copilot harness in Copilot Studio to general...
Building AI Pipelines on Azure Logic Apps: Lessons from the Consumption Plan
TL;DR – Azure Logic Apps Consumption is not the same as Logic Apps Standard, and the documentation will not always tell you that until you have already...
Building AI? Here’s where vibe coding actually fits in the process
TL;DR: Vibe coding gets a bad rap from people who think the only valid code is code you typed character by character. They are missing the point entirely. The...
Microsoft Scout: The Always-On AI Agent That Works While You Sleep
⚡ TL;DR Microsoft Scout, announced at Build 2026, is an always-on AI agent that works autonomously across Teams, Outlook, OneDrive, and SharePoint...
I’ve spent 4 years building production AI. Here’s what the LinkedIn posts don’t tell you
TL;DR: Social media is full of big AI talk from people who have never shipped a line of it. The real work - requirements, architecture, prompt engineering,...
Claude Fable 5 Was the Most Exciting Model Drop of 2026. Then the US Government Stepped In
TL;DR: Anthropic launched Claude Fable 5 on June 9, 2026 - the first publicly available Mythos-class model and the most capable AI Anthropic has released. It...
New vs Old Azure AI Foundry: How it affects your code
TL;DR I had a Foundry agent throwing a flat 400 invalid_payload on every call. The message was blunt: Not allowed when agent is specified. It turned out...
Power Platform at Scale: Auditing Every Connector Across Your Entire Tenant
TL;DR Before you touch a single DLP policy in Power Platform, you need to know what connectors are actually in use across your tenant. I built a...
The LLM Arms Race Has a Scoreboard. Here’s What It’s Telling You.
TL;DR - The SWE-bench leaderboard is the closest thing we have to an objective measure of which LLM is actually useful for software engineering. Right now,...
