Transcribed
Microsoft Agent Framework - Simply Explained
Jul 23, 2026 ·
15m 9s
Download and listen anywhere
Download your favorite episodes and enjoy them, wherever you are! Sign up or log in now to access offline listening.
Microsoft Agent Framework - Simply Explained
Description
AI agents are everywhere in headlines, yet few people can explain what they are or which framework to build them with. This episode is for developers, IT leaders and business...
show more
AI agents are everywhere in headlines, yet few people can explain what they are or which framework to build them with. This episode is for developers, IT leaders and business decision makers exploring agents in Microsoft environments. You learn what Microsoft Agent Framework is, how its building blocks work and where it fits next to Foundry, Copilot Studio and Microsoft 365 Copilot.
In this episode
Key takeaways
Worth quoting
“So think about the difference, a chatbot is reactive, it waits for your next question. An agent is proactive, you give it a goal and it goes off and works on it.” – Mirko Peters (01:47)
“What makes something an agent is the combination of three things. Reasoning, the ability to think through a problem. Tools, the ability to act on the world. And memory, the ability to remember what happened before” – Mirko Peters (02:31)
Explore more on M365.FM
Follow and rate M365.FM in your podcast app, and join the free M365 community at m365con.net.
Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-microsoft-365-azure-cloud-power-platform-ai--6704921/support.
show less
In this episode
- 00:00 – Why agents are more than chatbots
- 02:46 – Before the framework: a fragmented landscape
- 04:25 – What Microsoft Agent Framework is
- 06:22 – Building blocks: agents, tools, memory, workflows
- 08:40 – Practical value for business and IT
- 10:37 – How it fits with Foundry, Copilot Studio and Copilot
- 12:42 – Getting started
Key takeaways
- An AI agent combines reasoning, tools and memory so it can plan and act toward a goal instead of only answering questions like a chatbot.
- Microsoft Agent Framework unifies Semantic Kernel and AutoGen into one open-source SDK for Python and .NET with agents, workflows, MCP tools, memory and human-in-the-loop approvals.
- Developers build with the framework and deploy to Foundry, while Copilot Studio offers a low-code path, and both let organizations replace shadow AI with governed agents in Teams and Copilot.
Worth quoting
“So think about the difference, a chatbot is reactive, it waits for your next question. An agent is proactive, you give it a goal and it goes off and works on it.” – Mirko Peters (01:47)
“What makes something an agent is the combination of three things. Reasoning, the ability to think through a problem. Tools, the ability to act on the world. And memory, the ability to remember what happened before” – Mirko Peters (02:31)
Explore more on M365.FM
- Episode page: the full episode with chapters, key quotes and an FAQ on agents
- AI agent – defined here as reasoning, tools and memory working toward a goal, unlike a chatbot
- Copilot Studio – the low-code path for non-developers, complementing the framework's code-first approach
- Microsoft Foundry – where agents built with the framework are deployed, run and monitored in production
- Related episode: Microsoft Foundry Agent Service - Simply Explained
Follow and rate M365.FM in your podcast app, and join the free M365 community at m365con.net.
Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-microsoft-365-azure-cloud-power-platform-ai--6704921/support.
Information
| Author | Mirko Peters M365, Azure & AI |
| Organization | m365 FM |
| Website | www.m365.fm |
| Tags |
Copyright 2026 - Spreaker Inc. an iHeartMedia Company
Comments