Welcome to this AI Agent & Copilot Podcast, where we analyze the opportunities, impact, and outcomes that are possible with AI.
In this episode, I speak with Will Hawkins and Rich Hakwins of RitewAI regarding the forthcoming Microsoft Agent Framework and their impressions based on testing the open-source platform for building, orchestrating, and deploying AI agents
Highlights
Microsoft Agent Framework Overview and Introduction (1:36)
Will explains that the new framework effectively combines Semantic Kernel and AutoGen. Semantic Kernel was a cornerstone of Azure AI Agent Service and Copilot Studio. AutoGen is a research project on multi-agent orchestration systems. The agent framework simplifies the stack and adds newer features, supporting complex multi-agent actions.
Graph Based Workflow Functions (2:51)
Rich explains that graph-based workflows simplify orchestration, offering pre-made orchestration options like concurrent, sequential, and group chat. Custom workflows can be created using declarative workflows, which use a YAML string or document. An example of a process is orchestrating multiple agents for sales lead data prioritization and email drafting.
Multi-Vendor Support (5:14)
Will discusses the importance of being able to choose model providers due to potential outages or changes. (The Anthropic Claude outage that was taking place at the time the discussion was recorded is a good example.) The agent framework also allows users to bring their own models, which is crucial for specific use cases like lead identification or analysis.
The framework also support Agent2Agent (A2A) and Model Context Protocol (MCP); Rich explains that these protocols enable the integration of pre-made agents or tools into workflows. Will adds that they allow for a more seamless integration of different agents and tools, similar to connecting Lego bricks. The protocols enhance workflow and orchestration capabilities by enabling agents to share tools and communicate more effectively.
Community Support (9:29)
Rich evaluates the documentation and open-source community support positively, highlighting an active Discord channel and weekly office hours. Will emphasizes the open source nature of the agent framework and the collaborative approach from Microsoft. The community is actively involved in developing and contributing to the framework. The open source mindset encourages collaboration and innovation among developers.
Framework Comparisons (10:56)
Will Hawkins notes their focus on Microsoft tools, but they have compared it with open-source projects like Langchain. The key differentiator is the central governance by Microsoft, blending community-driven innovation with central management. Rich adds that the managed runtime and SDK by Microsoft provide a stable and reliable foundation for development.
More AI Development Insights:
- How to Choose the Right Microsoft Tools for Your AI Agent Orchestration Use Cases
- Why MCP Is Becoming the Universal Interface to Enterprise Data
- Agentic Workflows Bring New Levels of Automation to GitHub
