Speaker

Daniel Costea

Daniel Costea

Senior Software Engineer, Microsoft MVP

The Hague, The Netherlands

Microsoft MVP on Developer Technologies.
Developer. Speaker. Trainer.

Daniel Costea is a senior software engineer with more than two decades of experience and a passion for C# since its inception in 2001. He has been a frequent international speaker in Europe and the US in the past 6 years, and has organized community meetings and workshops. As a trainer, Daniel has delivered over 1200 hours of training in .NET web technologies to more than 700 students. He is also a published author of articles on .NET technologies, and was recognized as a Microsoft MVP in developer technologies in 2019.

Awards

Area of Expertise

  • Information & Communications Technology

Topics

  • ASP.NET
  • C#
  • IoT
  • Raspberry Pi
  • WebAPI
  • Machine Learning
  • .NET
  • ML.NET
  • OpenAI
  • LLMs

Unleashing the Power of Microsoft Semantic Kernel in API Communication - A Deep Dive into the GPT-4

Microsoft Semantic Kernel (SK) is a new technology that enables the integration of AI Large Language Models (LLMs) with conventional programming languages like C#, Python and Java. SK brings together several key components to provide planning and execution capabilities. These components include a robust kernel that provides the foundation for all other components, plugins (formerly known as skills) for performing specific tasks, connectors for interfacing with external systems, memories for storing information about past events, steps for defining individual actions, and pipelines for organizing complex multi-stage plans.

What about if we go beyond those clicks and build a semantic interface (code in C#) for an existing API (controlling a Car Robot)?

Talk To Your Code Using Microsoft Semantic Kernel

Microsoft Semantic Kernel (SK) is a new technology that enables the integration of AI Large Language Models (LLMs) with conventional programming languages.
SK is a powerful system that brings together several key components to provide planning and execution capabilities. These components include ASK (Active Semantic Knowledge) for understanding the user’s goals and context, GET (Goal Execution Technology) for creating and executing plans, and a robust Kernel that provides the foundation for all other components. SK also includes Skills for performing specific tasks, Connectors for interfacing with external systems, Memories for storing information about past events, Steps for defining individual actions, and Pipelines for organizing complex multi-stage plans.
We will explore several use-cases using multi-modal prompts and show how SK can be used to create and execute complex plans using a combination of natural language and conventional programming language like C#.

AI powered car robot using IoT Libraries and ML.NET

In this talk, we will showcase how to build an AI-powered car robot using IoT libraries and ML.NET. We will start by discussing the hardware components such as Raspberry Pi, video camera and sensor required to build the robot. Then, we will delve into the software side of things, covering the integration of IoT libraries and ML.NET to enable object detection and deep learning capabilities for the robot. We will demonstrate how to use ML.NET to train and deploy object detection models, and how to use IoT libraries to control the robot's movement and receive sensor data. Whether you are a hobbyist or an experienced developer, this talk will provide you with practical tips and techniques to build your own AI-powered car robot using IoT libraries and ML.NET.

OpenAI Assistants orchestrated with Semantic Kernel Agents

Creating agents with the Microsoft Semantic Kernel using OpenAI Assistants is an intriguing approach for handling complex problem-solving tasks. It uses AI to coordinate the work among multiple assistants. Each assistant has its own persona and tools, operating as separate GPTs. The days of manually managing conversation states and chat threads are behind us. Now, with the support of these assistants, we can have conversations that remember their context.

In this session I explore how these assistants can interact in three different scenarios:
- hierarchical chat agents (interactive chat)
- joint chat agents (interactive chat)
- agent powered by agents as plugins chat (one prompt chat)

For this, I have created four agents, each representing a different hero: Jack Sparrow, Don Quixote, Shakespeare, and Yoda. Additionally, I have a dialogue writer agent that takes a dialogue script and brings these heroes to life.

Well, let's see what happens when Jack Sparrow is messing up with Don Quixote!

OpenAI, Azure OpenAI, Visual Studio Code, C#
For developers.

A Dash of .NET User group Sessionize Event

March 2024

Developer Week '23 Sessionize Event

June 2023 Nürnberg, Germany

Developer Week '21 Sessionize Event

June 2021 Nürnberg, Germany

Virtual Scottish Summit 2021 Sessionize Event

February 2021

CodeGen 2021 Sessionize Event

February 2021

dotNet OpenSource Days 2020 Sessionize Event

December 2020

.NET DeveloperDays 2020 Sessionize Event

October 2020 Warsaw, Poland

.NET Virtual Conference Sessionize Event

October 2020

.NET Core Summer Event 2020 Sessionize Event

June 2020

The Virtual ML.NET Community Conference Sessionize Event

May 2020

Cloud DeveloperDays 2020 Sessionize Event

May 2020

Vermont Code Camp 2018 Sessionize Event

September 2018 Burlington, Vermont, United States

ITCamp 2018 Sessionize Event

June 2018 Cluj-Napoca, Romania

Daniel Costea

Senior Software Engineer, Microsoft MVP

The Hague, The Netherlands