As I was writing these other post and coding the agents, I was having some doubts about whether or not they agents were actually running or not. I did add some Terminal prompting but there was still some doubt. I needed to discover some additional perspectives on how to monitor and measure my AI Agents […]
Read More →In my last post Advanced multi-agent orchestration architectures I wrote about Hub-and-Spoke, Hierarchical, and Supervisor patterns. In this article, as the title makes clear I will get a bit deeper into hub-and-spoke. But before that, as I was writing the hub and spoke code I learned a few hard lessons. I share them in case […]
Read More →
In a previous article, The difference between Agentic AI and Multi-Agent Architectures, I touched on multi-agent systems and briefly on pattern selection. This article will discuss those 3 patterns in more detail. In this article, Orchestrate a multi-agent solution using the Microsoft Agent Framework flat / foundational orchestration patterns were discussed. They are Concurrent, Sequential, […]
Read More →
Every multi-agent system is agentic, every agentic system is not multi-agent. You can see textually some differences between them in Table 1 and Figure 1. An Agentic system is one which would respond to and infer the following prompt: The autonomous Agentic AI chooses the action instead of executing a pipeline or multiple agents. The […]
Read More →
As I consume AI NLP responses I very often accept without much resistance, second guessing, or contemplation for or against the result presented to me. I simply read it and if I agree, I take it as true and continue forward with my activity. If I don’t agree I tend to respond with my doubt […]
Read More →The Agent-to-Agent (A2A) protocol is a method for utilizing AI Agents which are not cohosted together. For example, you have AI Agent X located at an HTTPS address #1 and AI Agent Y hosted at HTTPS address #2 and AI Agent Z that runs from a Chat and needs to utilize X and Y. This […]
Read More →
The Microsoft Agent Framework is an open-sourced SDK which combines the Semantic Kernel and AutoGen into a single, highly innovative set of AI capabilities into a single library. AI features like: Unified model connectivity and chat clients for OpenAI, Azure OpenAI, Anthropic, Ollama, and other leading LLM providers. Multi-agent orchestration, allowing specialized AI agents to […]
Read More →