// tag
#Agents
26 posts
Microsoft Foundry June 2026: From Feature Drops to a Governed Agent Platform
June’s Foundry updates signal a platform transition: distribution, tooling, memory, observability, and optimization are converging into an enterprise-ready agent operations stack.
The May 2026 Azure SDK Release Has a Few Things .NET Developers Should Not Ignore
The Azure SDK May 2026 release is broad, but three themes stand out: Azure AI Search knowledge bases, new Agent Server libraries, and the growing cross-language maturity of the Azure SDK ecosystem.
Deep Agents + Cosmos DB Show a Practical Pattern for Working Against Live Operational Data
The Deep Agents sample with Azure Cosmos DB is interesting because it shows an agent working directly on operational data, planning across multiple steps, verifying writes, and staying grounded in the same store the business already uses.
OpenEnv + Foundry Push the Conversation Beyond Static Agents
The new OpenEnv and Foundry story is about much more than reinforcement learning buzzwords. It is really a push toward agent systems that can be evaluated, optimized, and improved over time against real business outcomes.
AI Alone Won’t Change the Business — the System Around It Will
Jay Parikh’s latest AI platform essay is worth reading because it frames the real enterprise challenge correctly: models matter, but the lasting value comes from the governed system that builds, contextualizes, runs, and improves agents over time.
Claude Fable 5 in Foundry Changes the Ceiling for Autonomous Agents
Claude Fable 5 is now in Microsoft Foundry, and the real story is not just a stronger model. It is that teams can pair long-running reasoning with Foundry's governance, memory, and deployment stack.
A WinUI Agent Plugin for GitHub Copilot and Claude Code
Microsoft released agent skills for WinUI development — scaffold, build, run, test, iterate, all with GitHub Copilot CLI or Claude Code. The key innovation: purpose-built tools that ground the agent in WinUI-specific facts.
Agent Harness, Hosted Agents, and CodeAct: This Is the Agent Framework Update I Would Focus On
The Build 2026 Agent Framework announcement is packed, but the most important threads are the harness model, Foundry hosted agents, and CodeAct for reducing orchestration overhead.
The Agent Framework Sessions From Build 2026 Worth Following
The latest Microsoft Agent Framework Build guide is useful as a map of where the platform conversation is going: hosted agents, observability, governance, multi-agent design, and open interoperability.
Agent Skills in Visual Studio: Teach Copilot How Your Team Actually Works
Visual Studio now supports Agent Skills — reusable instruction sets that teach Copilot your team's specific workflows, coding standards, and conventions. Define once, apply automatically.
Marketplace Is Becoming Part of the Agent Platform Story Too
Microsoft Marketplace is increasingly being positioned as part of the app-and-agent lifecycle: not just discovery, but build sourcing, distribution, monetization, and in-product surfacing.
NL2SQL Is the SQL Injection of the Agentic Age
Before you let an agent query your database with natural language, read this. NL2SQL looks simple until you think through schema completeness, indeterminism, and what SQL MCP Server actually solves.
Microsoft Foundry May 2026: The Updates I’d Actually Watch Closely
The latest Microsoft Foundry roundup covers a lot, but the most important threads are trace-based evaluation, new model choice, managed isolation, and the continued rise of local and production-grade agent tooling.
Foundry’s Observability-to-ROI Story Is What Serious Agent Platforms Need
The latest Foundry observability announcement matters because it connects tracing, evaluation, optimization, and ROI into one operating loop for AI agents.
Your AI Agent Has an Identity Problem (And Here's the Template That Solves It)
A new azd template from Curity and Microsoft shows how to build AI agents that use short-lived OAuth tokens with fine-grained scopes — so agents can never see data they shouldn't.
CodeAct in Agent Framework: How to Cut Your Agent's Latency in Half
CodeAct collapses multi-step tool chains into a single sandboxed code block — cutting latency by 52% and token usage by 64%. Here's what it means for your agents and when to reach for it.
Where Does Your Agent Remember Things? A Practical Guide to Chat History Storage
Service-managed or client-managed? Linear or forking? The architectural decision that shapes what your AI agent can actually do — with code examples in C# and Python.
Foundry Toolboxes: One Endpoint for All Your Agent Tools
Microsoft Foundry just launched Toolboxes in public preview — a way to curate, manage, and expose AI agent tools through a single MCP-compatible endpoint without re-wiring everything per agent.
VS Code 1.117: Agents Are Getting Their Own Git Branches and I'm Here For It
VS Code 1.117 ships worktree isolation for agent sessions, persistent Autopilot mode, and subagent support. The agentic coding workflow just got way more real.
Where Should You Host Your AI Agents on Azure? A Practical Decision Guide
Azure offers six ways to host AI agents — from raw containers to fully managed Foundry Hosted Agents. Here's how to pick the right one for your .NET workload.
Azure MCP Server 2.0 Just Dropped — Self-Hosted Agentic Cloud Automation Is Here
Azure MCP Server 2.0 goes stable with self-hosted remote deployments, 276 tools across 57 Azure services, and enterprise-grade security — here's what matters for .NET developers building agentic workflows.
Agentic Platform Engineering Is Getting Real — Git-APE Shows How
Microsoft's Git-APE project puts agentic platform engineering into practice — using GitHub Copilot agents and Azure MCP to turn natural-language requests into validated cloud infrastructure.
Microsoft Foundry March 2026 — GPT-5.4, Agent Service GA, and the SDK Refresh That Changes Everything
Microsoft Foundry's March 2026 update is massive: Agent Service hits GA, GPT-5.4 brings reliable reasoning, the azure-ai-projects SDK goes stable across all languages, and Fireworks AI brings open models to Azure.
VS Code 1.116 — Agents App Gets Keyboard Navigation and File Context Completions
VS Code 1.116 focuses on Agents app polish — dedicated keybindings, accessibility improvements, file-context completions, and CSS @import link resolution.
azd Now Lets You Run and Debug AI Agents Locally — Here's What Changed in March 2026
The Azure Developer CLI shipped seven releases in March 2026. The highlights: a local run-and-debug loop for AI agents, GitHub Copilot integration in project setup, and Container App Jobs support.
Foundry Agent Service is GA: What Actually Matters for .NET Agent Builders
Microsoft's Foundry Agent Service just hit GA with private networking, Voice Live, production evaluations, and an open multi-model runtime. Here's what you need to know.