Durable Workflows In Microsoft Agent Framework
My earlier article on workflows in MAF was focused on implementing them within a Console application. Those types of workflows run entirely in memory through an in-process runner. Another article focu

Search for a command to run...
My earlier article on workflows in MAF was focused on implementing them within a Console application. Those types of workflows run entirely in memory through an in-process runner. Another article focu

In a typical Agent AI and Workflow setups when something goes wrong major questions start piling up: Which agent handled the request? Which tool was invoked? How long did each step take? Where did

The Agent-User Interaction Protocol or commonly known as AG-UI is a protocol developed to expose AI agents to web/mobile frontends. Think of AG-UI as HTTP protocol for AI Agents. With AG-UI its now po

My previous article focused on Multi Agent Orchestration in Azure Durable Functions for Microsoft Agent Framework. The use case used in the article was pretty straightforward wherein there were two ag

In my previous article, I introduced the process of setting up a single durable agent using the Azure Durable Framework and the Docker-based Durable Task Scheduler (DTS) Emulator. This article will be

Azure Durable Functions are an extension of Azure Functions that makes it easy to build long-running, stateful workflows in serverless environments. Instead of managing state, retries, checkpoints and

The general approach for Human-In-The-Loop (HITL) in Microsoft Agent Framework is through ToolApprovalRequestContent driven by AIFunction invocation wrapped around ApprovalRequiredAIFunction. But for

Human-In-The-Loop or commonly called as HITL is a common design pattern across multi agent setups that requires human approval or intervention at critical stage of a multi agent execution process. In

Imagine you have a Microsoft Agent Workflow that continuously processes a high-volume stream of incoming data. The data flows through multiple executors responsible for validation, summarization and d
