Welcome to the AI Copilot Podcast, analyzing the latest AI Copilot and agent developments from Microsoft and its partners, delving into customer use cases, and exploring how AI plus Cloud helps customers reimagine business. In this episode, Tom Smith shares new agentic AI developments from Microsoft.
Highlights
00:33 — Microsoft introduced a new AI agent development and orchestration framework in Microsoft Azure AI Foundry — an extension of Azure AI Foundry’s open-source Semantic Kernel that is designed to simplify orchestration in multi-agent systems.
01:10 — Azure AI Foundry provides a feedback system designed to enable continuous improvement of agents through real-time telemetry and user feedback. This is complemented by Microsoft’s advanced observability capabilities giving developers strong visibility into agent behaviors and outcomes.
AI Agent & Copilot Summit is an AI-first event to define opportunities, impact, and outcomes with Microsoft Copilot and agents. Building on its 2025 success, the 2026 event takes place March 17-19 in San Diego. Get more details.
01:48 — Organizations including KPMG and Fujitsu are using Semantic Kernel to orchestrate workflows among specialized agents and in so doing, they report dramatically reducing development complexity.
02:58 — Microsoft also introduced AI Red Teaming Agent, which systematically probes AI models to uncover safety risks; it generates reports and tracks improvements over time, creating an AI safety testing ecosystem. Plus, new agentic evaluations provide risk and quality assessments that empower teams to build trustworthy and advanced AI agents. These evaluation metrics help teams identify and mitigate potential risks in agent behavior, providing another layer of security and compliance.
Ask Cloud Wars AI Agent about this analysis
