Author Archives: Jesse Liberty

Unknown's avatar

About Jesse Liberty

Jesse Liberty has three decades of experience writing and delivering software projects and is the author of 2 dozen books and a couple dozen online courses. Liberty is a Senior AI Engineer at the University of Pittsburgh Medical Center, and was a Team Lead and Senior Software Engineer for various corporations, a Senior Technical Evangelist for Microsoft, a Distinguished Software Engineer for AT&T, a VP for Information Services for Citibank and a Software Architect for PBS. He is a 21 year Microsoft MVP.

RAG in Microsoft Agent Framework – Overview

Microsoft’s Agent Framework treats retrieval as a first‑class capability so agents can fetch only what they need (or always fetch), attach source metadata, and call search as a tool during reasoning. The result: more efficient, auditable, and controllable Retrieval‑Augmented Generation … Continue reading

Posted in AI | Leave a comment

16 Week Johns Hopkins Program on Agentics

~2 hours a day for 16 weeks + 3 projects. Excellent program.

Posted in AI | Comments Off on 16 Week Johns Hopkins Program on Agentics

CoPilot Harness and Microsoft Agent Framework

Our friends at Microsoft have paired our development tool (CoPilot) with Microsoft Agent Framework. This powerful combination allows developers to create intelligent agents that can automate tasks, enhance productivity, and streamline workflows. This blog post will explore how to effectively … Continue reading

Posted in AI | Comments Off on CoPilot Harness and Microsoft Agent Framework

Deploying to Foundry

When it comes to deploying Microsoft Agent Framework applications, Microsoft Foundry offers a robust platform that simplifies the process. This guide will walk you through one approach to deploying your application.

Posted in AI | Comments Off on Deploying to Foundry

Reducing Token Usage

If you want to hold costs down, efficient resource management is paramount. One of the critical resources in AI applications is token usage. Tokens are the basic units of text that models process, and managing them effectively can lead to … Continue reading

Posted in AI | Comments Off on Reducing Token Usage

About Neo4j

In the previous blog post I mentioned Neo4j. In this post I will provide an overview of this important framework. A Graph Database In the era of big data, the way we store and manage information has evolved significantly. Traditional … Continue reading

Posted in AI | Comments Off on About Neo4j

An Overview of Agent Memory for .NET

The ability for Microsoft Agent Framework agents to retain and utilize knowledge across interactions is critical. One solution for this is Agent Memory for .NET, a cutting-edge, mind-blowing, graph-native memory engine that leverages the robust capabilities of Neo4j as its … Continue reading

Posted in AI, Essentials | Comments Off on An Overview of Agent Memory for .NET

Microsoft Agent Framework and Foundry

In the .NET development world the two most significant frameworks for AI are Microsoft Agent Framework and Microsoft Foundry. Together, they create a powerful ecosystem for building, deploying, and managing AI agents that can automate tasks, respond to user queries, … Continue reading

Posted in AI, Foundry, Microsoft Agent Framework | Comments Off on Microsoft Agent Framework and Foundry

Managing Secrets in Microsoft Agent Framework

In the realm of software development, managing configuration values and sensitive information is a critical aspect that can significantly impact the security and functionality of applications. Developers often find themselves at a crossroads when deciding how to store configuration values, … Continue reading

Posted in AI | Comments Off on Managing Secrets in Microsoft Agent Framework

Detecting AI

I fed the first half of one of the blog posts generated by my demonstration program to Pangram. Here are the results: Bzzzz Still your turn.

Posted in AI | Comments Off on Detecting AI

ChatClient Middleware vs. Agent Middleware

As noted in a previous post, middleware plays a pivotal role in enhancing the functionality and observability of agents. The Microsoft Agent Framework utilizes two primary types of middleware: ChatClient Middleware and Agent Middleware. Understanding the distinctions between these two … Continue reading

Posted in AI, Essentials | Comments Off on ChatClient Middleware vs. Agent Middleware

Long-term memory in Microsoft Agent Framework

Long-term memory in AI agents refers to the ability to retain information across multiple interactions and sessions. This is essential for creating a more personalized user experience, as it allows agents to recall user preferences, past conversations, and contextual information. … Continue reading

Posted in AI | Comments Off on Long-term memory in Microsoft Agent Framework