Build controlled agentic workflows with Microsoft Agent Framework and C# using executors, edges, shared state, conditional routing, AI reasoning, and multiple execution paths.

Connect Microsoft Agent Framework to real system data using C# functions and MCP, then pass deterministic evidence to an AI agent for risk analysis.

Learn when to use an Agent, Workflow, or deterministic function in Microsoft Agent Framework, and how to combine them to build controlled production-grade agentic systems.

Understand Microsoft Agent Framework architecture in .NET, from agents and sessions to workflows, middleware, context providers, and the key Agent vs Workflow decision.

Build your first tool-enabled AI agent with Microsoft Semantic Kernel. Learn how a single agent retrieves external information, makes decisions, and performs controlled actions using automatic function calling.

Learn how Microsoft Semantic Kernel transforms isolated LLM calls into orchestrated AI workflows by coordinating reasoning, plugins, memory, and application logic.

A deep dive into the core concepts behind Microsoft Semantic Kernel, explaining how Kernel, Plugins, Memory, and Orchestration work together to move from prompt-based AI to production-grade AI systems.

Discover why Microsoft created Semantic Kernel and how it helps developers move beyond prompt engineering to build scalable AI systems using orchestration, memory, plugins, and AI agents.

Learn how to conduct a one-sample T-test for a population mean using hypothesis testing, T-scores, and critical values. Understand when and why to use the T-distribution.

Learn how to perform a one-tailed or two-tailed Z-test for a population proportion. This guide walks through hypothesis setup, Z-score calculation, and P-value interpretation with a real-world case.