RC
Cloud Native Agentic AI Infrastructure
Blog Books Courses Newsletter About
Blog Books Courses Newsletter About
Home
Recent
Microsoft Agent Framework Agents Production 📚 Microsoft Agent Framework

Human-in-the-loop with function approvals in Microsoft Agent Framework

Mar 20, 2026

Some tool calls are too consequential to let an agent run unsupervised. Function approvals pause the agent run when a destructive or sensitive tool is about to fire, surface the call to a human, and resume only after explicit approval. This article looks at how to mark a tool as approval-required, how the run pauses, and how to wire approve and reject back into the agent.

Home
Recent
Microsoft Agent Framework Workflows 📚 Microsoft Agent Framework

Visualizing and checkpointing workflows in Microsoft Agent Framework

Mar 18, 2026

A workflow is a graph that runs in discrete supersteps. That structure makes two things easy that are usually hard: drawing the graph, and pausing the run cleanly so you can resume it later. This article looks at WorkflowViz for visualization and the CheckpointStorage system for persistence.

Home
Recent
Microsoft Agent Framework Workflows 📚 Microsoft Agent Framework

Workflow fundamentals in Microsoft Agent Framework

Mar 16, 2026

Sequential, concurrent, handoff, group chat, and magentic workflows are all built on the same four primitives: executors, edges, events, and a superstep-based execution model. This article looks at those primitives directly, so you know what is happening underneath when you reach for an orchestration builder, and so you can build workflows the builders do not cover.

Home
Recent
Microsoft Agent Framework Agents Memory 📚 Microsoft Agent Framework

Context providers and pluggable memory in Microsoft Agent Framework

Mar 15, 2026

AgentSession keeps one conversation alive for as long as the Python process runs. Context providers let an agent remember things across sessions, across users, and across long timescales. This article looks at the provider abstraction, the built-in history and memory providers, and how to write your own.

Home
Recent
Microsoft Agent Framework Tools MCP 📚 Microsoft Agent Framework

Exposing Microsoft Agent Framework agents as MCP servers

Mar 10, 2026

We have spent the last two articles consuming MCP servers from a MAF agent. This one flips the picture: how to publish a MAF agent as an MCP server so that other agents and applications, in any framework, can call it as a tool.

Home
Recent
Microsoft Agent Framework Tools MCP Foundry 📚 Microsoft Agent Framework

Hosted MCP tools in Microsoft Agent Framework

Mar 9, 2026

Foundry can host the MCP connection on the agent's behalf. This article looks at how a hosted MCP tool differs from the local MCP setup we built last time, where authentication moves, and how to wire one up via FoundryChatClient.get_mcp_tool.

Featured
Google Agent Development Kit Agents Skills 📚 Google ADK

Google ADK - Agent Skills

Feb 28, 2026

Dive into a powerful new feature in Google ADK: Agent Skills. We will explore what Agent Skills are, why they matter, and how to implement a practical use case.

Featured
Hugo AI Agents LLMs

Implementing llms.txt and Markdown Output in Hugo

Feb 16, 2026

Learn how to extend Hugo to generate llms.txt and clean Markdown versions of your content, making your site easily consumable by AI agents and LLMs.

Featured
Agent Skills MCP 📚 Agents

Agent skills vs Model Context Protocol - [How] do you choose?

Feb 6, 2026

Agent Skills and MCP are a hot topic. Understanding these standards genuinely overlap, where they serve fundamentally different purposes, and where each falls short, is essential for anyone building agent-powered systems.

📚 Series

Microsoft Agent Framework

22 articles

  • • Human-in-the-loop with function approvals in Microsoft Agent Framework
  • • Visualizing and checkpointing workflows in Microsoft Agent Framework
  • • Workflow fundamentals in Microsoft Agent Framework
  • ... and 19 more
📚 Series

Model Context Protocol

2 articles

  • • Building a Model Context Protocol server for Azure
  • • Model Context Protocol by Anthropic for connecting AI models to data
📚 Series

Google ADK

10 articles

  • • Google ADK - Agent Skills
  • • Building multi-agent systems with Google ADK and the A2A protocol
  • • Building a Multi-Agent LinkedIn Newsletter System with Google ADK
  • ... and 7 more

© 2026 Ravikanth Chaganti. All rights reserved.

This site may load third-party content (comments, embeds) that could set cookies. Learn more

Cookie Preferences

Control what third-party content is loaded. We use privacy-friendly analytics with no cookies.

Essential

ON

Required for the website to function. Cannot be disabled.

  • • Theme preference
  • • Privacy-friendly analytics

Comments

Giscus comment system (GitHub Discussions).

  • • Authentication cookies
  • • GitHub privacy policy

Embedded Content

Videos, code snippets, presentations.

  • • YouTube, Gists, SlideShare
  • • May set tracking cookies

Privacy First

No tracking cookies. Third-party content only loads with your consent. Preferences stored locally in your browser.