azure-ai - The LGTM (Page 2)

The LGTM

Sign in Subscribe

azure-ai

A collection of 130 posts

Microsoft Foundry Is Pitching OpenEnv as the Enterprise Agent Training Loop, Not Another Chatbot Stack

Microsoft Foundry Is Pitching OpenEnv as the Enterprise Agent Training Loop, Not Another Chatbot Stack

Microsoft’s latest Foundry post is not selling another chatbot. Good. The industry has enough demo loops that answer once, forget everything, and then get celebrated as “agentic” because they called a tool. The more interesting claim is that enterprise AI systems need gyms: controlled environments where agents can practice

Microsoft's Agent-Skill Advice Is Brutal and Correct: Stop Shipping Textbooks to the Context Window

Microsoft's Agent-Skill Advice Is Brutal and Correct: Stop Shipping Textbooks to the Context Window

Microsoft’s best agent advice this week is not a new model, a bigger context window, or another “autonomous” demo that quietly assumes the happy path. It is Waldek Mastykarz telling developers to stop overloading agent skills. Brutal, correct, and apparently still necessary: most teams do not need to ship

Copilot Code Review Reads AGENTS.md Now. Good: Review Policy Belongs in the Repo, Not in Someone's Head

Copilot Code Review Reads AGENTS.md Now. Good: Review Policy Belongs in the Repo, Not in Someone's Head

GitHub Copilot code review learning to read AGENTS.md is not the flashiest AI announcement of the week. Good. The useful agent features rarely are. This one matters because it moves AI review away from generic “looks plausible” commentary and toward something software teams have needed from the start: repo-local

Copilot Usage Metrics Just Got Less Wrong — Now Admins Need to Relearn Their Baselines

Copilot Usage Metrics Just Got Less Wrong — Now Admins Need to Relearn Their Baselines

GitHub made Copilot usage metrics more accurate, which is good news in the same way a scale getting calibrated is good news: useful, necessary, and immediately dangerous if everyone forgets the baseline changed. The June 15 update adds server-side telemetry to Copilot reports, so enterprise dashboards will include more active

GitHub Code Quality GA Turns AI Review Into a Three-Part Bill

GitHub Code Quality GA Turns AI Review Into a Three-Part Bill

GitHub Code Quality is leaving preview, and the feature announcement is not the part engineering leaders should read twice. The pricing model is. On July 20, 2026, GitHub turns Code Quality into a paid product that combines a per-committer subscription, AI-credit consumption, and GitHub Actions minutes. That is not a

Work IQ GA Turns Microsoft 365 Context Into a Metered Agent Primitive

Work IQ GA Turns Microsoft 365 Context Into a Metered Agent Primitive

Microsoft just put a meter on one of the most valuable ingredients in enterprise AI: the context of work itself. Work IQ, Microsoft’s API layer for grounding agents in Microsoft 365 context, reaches general availability on June 16 with consumption-based pricing through Copilot Credits, according to Microsoft Partner Center.

Copilot Notebooks Just Moved From Premium Feature to Shared Team Context Layer

Copilot Notebooks Just Moved From Premium Feature to Shared Team Context Layer

Copilot Notebooks looks, at first glance, like one more Microsoft 365 surface where users can dump files and ask an AI to summarize them. That framing undersells the move. The useful story is that Microsoft is taking the most annoying part of workplace AI — getting the right context into the

The Agent Scaffold Trap: `npx` Can Succeed While Quietly Installing 2020

The Agent Scaffold Trap: `npx` Can Succeed While Quietly Installing 2020

The most dangerous failure mode in agentic coding is not the spectacular one where the model deletes production or invents an API. It is the quiet one where every command succeeds, files appear on disk, the agent reports progress, and the project starts six years in the past. Microsoft Developer

Microsoft's AI Investigation Playbook Turns Copilot Telemetry Into Incident Response Plumbing

Microsoft's AI Investigation Playbook Turns Copilot Telemetry Into Incident Response Plumbing

AI incident response has reached the boring phase, which is exactly when it starts to matter. Microsoft’s new investigator playbook for reconstructing AI activity across Microsoft 365 Copilot and Azure AI services is not the kind of announcement that wins a launch-day popularity contest. There is no new model,

Azure Skills 1.1.68 Is a Small Release With a Big Signal: Cloud Agents Need Approval Gates, Not Prompt Packs

Azure Skills 1.1.68 is a small release with a product lesson hiding in plain sight: cloud agents do not need more charming prompt packs. They need governed workflows that know when to stop. Microsoft’s Azure Skills Plugin repository merged PR #137 on June 9, an automated sync

Microsoft's Build Recap Makes the Azure AI Stack Look Less Like a Product Line and More Like an Agent Operating System

Microsoft's Build Recap Makes the Azure AI Stack Look Less Like a Product Line and More Like an Agent Operating System

Microsoft's official Build 2026 developer recap dropped on June 8, and if you read it as a roundup of new features, you will come away confused. The post names GitHub, Microsoft IQ, Foundry, Agent 365, Microsoft Security, Teams, and Microsoft 365 in roughly the same sentence, and the