// tag
#AI Agents
14 posts
Agent Optimizer Brings an Evaluation Loop to Foundry Agent Service
Foundry Agent Optimizer evaluates an agent, generates candidate configurations, ranks them, and promotes a winner without retraining the model.
Discovery to Execution: Scaling Agents with Toolboxes and Routines in Microsoft Foundry
How Tool Search, Skills, and Routines reduce the operational friction between an agent prototype and a production workflow.
Foundry IQ: Build Smarter Agents with Unified Knowledge and Serverless Retrieval
Foundry IQ combines permission-aware knowledge sources, agentic retrieval, and a serverless Developer tier so .NET teams can focus on agent behavior instead of retrieval plumbing.
VS Code 1.122: Remote Agent Tasks, Model Management, and Better Issue Reporting
The May 2026 release adds remote task triggers for agents, granular language-model management, changed-file search, and a richer issue reporter.
The New Plan Agent in Visual Studio Fixes a Very Real AI Workflow Problem
The new Plan agent in Visual Studio matters because it creates a structured planning stage before implementation, which is exactly what bigger features and refactors often need.
Run and Test AI Agents Locally with Azure Developer CLI
New azd AI agent commands shorten the inner loop by starting agents locally and invoking local or remote sessions from the terminal.
VS Code 1.128 Makes a Clear Bet: The Agents Window Is Becoming the New Work Surface
VS Code 1.128 turns agent workflows from novelty into daily ergonomics with multi-chat sessions, GA vision support, and deeper host/session controls.
VS Code’s GPT-5.5 Prompt Tuning Proves a Hard Truth: Harness Design Beats Hype
The VS Code experiment with GPT-5.5 shows measurable gains come from disciplined harness and prompt iteration, not just swapping to newer foundation models.
The Real Agent UX Win Is Safe Autonomy, Not Maximum Autonomy
File access, approvals, and memory design are the practical triad for trustworthy agent behavior in production.
The Agent Confidence Index Should Change What You Automate Next
The data says teams trust agents most for repetitive technical toil, not for high-stakes judgment calls.
Visual Studio 2026 April Update: Cloud Agent, Custom Agents, and Debugger Agent
Visual Studio 2026 (18.5) April update brings cloud agent integration, user-level custom agents, C++ code tools GA, and a Debugger Agent that validates fixes against live runtime behavior.
Governing MCP Tool Calls in .NET with the Agent Governance Toolkit
The Agent Governance Toolkit is a .NET 8+ package for scanning MCP tool definitions for threats, enforcing YAML-based policy, and sanitizing tool output — covering OWASP MCP Top 10.
Microsoft Agent Framework Part 3: From Tools to Workflows — The Building Blocks Click Into Place
Part 3 of the .NET AI building blocks series covers the Microsoft Agent Framework — from single agents with tools to multi-agent workflows with memory. Here's what actually matters.
SQL MCP Server on Azure App Service — No Containers Required
The SQL MCP Server can now run on Azure App Service without Docker or Kubernetes. Here's what that means for .NET developers building AI agents that talk to SQL databases.