GeekAcademy is a 3-month AI course for developers and is a part of Microsoft & Geektime's national initiative to empower Israel’s developers community. The course will help developers master AI tools like GitHub Copilot, AI Foundry and Visual Studio, with hands-on experience building AI agents and solutions. Participants will explore AI fundamentals, advanced techniques, and real-world applications, guided by Microsoft and GitHub experts.
<Syllabus>
</> GeekAcademy is intended for developers with at least 3 years of experience and basic knowledge of cloud and Python.
</> Our syllabus includes 12 online sessions and 3 in-person events.
</> Online sessions are open to all students, while the in-person events require additional
registration and must be approved in advance by email.
</> All online sessions include an expert hour provided by Microsoft and its partners.
GeekAcademy Studio: Agents, Robotics & Next level Github (In-Person)
📅February 20th 🕒09:30-12:00 🤝 Physical Event @ Microsoft Israel Campus in Herzliya
Our special kick-off event of GeekAcademy will host 100 students for a morning full of great content:
🤝 Opening Session: Alon Haimovich - GM {Microsoft Israel}
🤝 Fireside chat - Idan Gazit - Head of GitHub Next {GitHub} & Idan Ben Tovim - sr. Tech Reporter {Geektime}
🤝 Listen, Look, and Leap: The Journey of an Intelligent Robot: Amit Svarzenberg - CTO and AI lecture {Microsoft for Startups Israel}
🤝 Empowering Video Understanding with VLMs, LLMs and SLMs: Yonit Hoffman - Data Science Manager {Microsoft Israel R&D Center}
🤝 Summary and Looking Ahead to the Continuation of the Course: Adi Stein - Azure Digital & App Innovation GTM, {Microsoft SouthEast Europe} & Ben Haklai - National Technology Officer {Microsoft Israel}
To participate in this event - a seperate registration is required.
Additional Speakers:
Essential Prompting for GitHub Copilot In VS Code
📅February 25 🕒10:00-11:15 💻 Online Webinar
In this session, you will learn how to set up GitHub Copilot in VS Code and then use it to do some interesting things that will save you time and effort.
Learning Outcomes:
👨🏻💻Use the Copilot Chat window, along with chat participants and variables, to brainstorm solutions for your project.
👩🏻💻Use inline chat in the editor to refactor and document your code.
👩🏻💻Use inline chat in the terminal to execute time-saving commands.
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Moti Malka
Mastering LLMs: Fundamentals & Practical Applications
📅March 4th 🕒10:00-11:15 💻 Online Webinar
Discover the basics of generative AI, including core models, and functionalities. Learn how to utilize these models within the Azure ecosystem, leveraging various services to build your own generative AI applications.
Learning Outcomes:
👨🏻💻Learn about the history of AI at Microsoft
👩🏻💻Explore the Azure AI services
👨🏻💻Understand how language models work
👩🏻💻Learn how to interact with large language models
👨🏻💻Explore various types of models for different use-cases
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Alon Fliess
VS Code & GitHub Copilot in the Wild – Advanced Productivity Hacks
📅March 11th 🕒10:00-11:15 💻 Online Webinar
Discover how GitHub Copilot can transform your approach to coding in this practical session! We will focus on solving real-world scenarios by using Copilot to understand and work within unfamiliar codebases. Participants will also learn how to create an extension from scratch and integrate the JFrog extension for improved open-source package management in their workflows. As we explore our repository and commit history, we'll delve into advanced prompting techniques to maximize Copilot’s utility. Come ready to engage and leave with actionable insights that you can immediately apply to your development projects.
Learning Outcomes:
👨🏻💻GitHub Copilot features can help in real-world scenarios
👩🏻💻Gain a thorough understanding of unknown codebases
👨🏻💻Speedup your development workflows with ease
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Aviv Kabesa
Prompt Engineering & AI Orchestration with Azure AI Foundry
📅March 18th 🕒10:00-11:15 💻 Online Webinar
When developing a generative AI application, selecting the right model is an essential first step. However, the true differentiator lies in how you utilize your input. In this session, you will discover how to maximize the potential of your model through advanced prompt engineering techniques, integrating your model with various data sources, and enabling it to perform actionable tasks. Additionally, you will learn how to leverage Azure AI Foundry as the ideal platform to start building custom AI solutions.
Learning Outcomes:
👩🏻💻Make the best out of the powerful models offered by Azure AI Foundry Model Catalog by leveraging Prompt Engineering techniques and best practices.
👨🏻💻Discover how to build, test and evaluate custom and multimodal AI solutions safely in Azure AI Foundry, thanks to built-in data connectors, AI orchestration toolchain and tracing facilities.
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Aviad Fenigstein
GeekAcademy 2nd Workshop: Next-Gen Software Development with GitHub Copilot Agents
📅March 24th 🕒09:30-14:30 🤝 Physical Event @ Microsoft Reactor Israel
🚀 GitHub Copilot Workshop – Elevate Your AI-Powered Development
Join us for the second in-person meetup of GeekAcademy - an interactive GitHub Copilot Workshop, designed to enhance your coding efficiency and streamline development with AI-driven assistance.
What You’ll Learn:
🔹 Foundations & Setup – Get started with GitHub Copilot and explore its capabilities.
🔹 Code Refactoring & Optimization – Leverage AI to improve existing code, generate documentation, and create unit tests.
🔹 Feature Development – Utilize prompt engineering techniques to build and refine new features with Copilot.
🔹 Integration & Automation – Enhance workflows by integrating Copilot with external tools and extensions.
🔹 Custom Extensions – Develop and test your own Copilot Chat extension for a tailored development experience.
This workshop is ideal for developers looking to maximize productivity, enhance code quality, and harness AI-driven tools for modern software development.
To participate in this event - registration to the course and an email approval is required.
AI Apps with Prompty: Production-Ready Development Made Easy
📅March 25th 🕒10:00-11:15 💻 Online Webinar
Integrating GenAI into traditional development can be daunting. Prompty simplifies LLM app development and works seamlessly with tools like Visual Studio Code and GitHub. Learn how to build multi-model LLM (agent) architecture, evaluation, deployment, and monitoring.
Learning Outcomes:
👨🏻💻How to get started with LLMs
👩🏻💻Understand the Prompty Specification
👨🏻💻How to get started with Prompty in Visual Studio Code
👩🏻💻How to develop an App with Prompty
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Sofi Mogilevsky
Getting Started with AI Agents
📅April 1st 🕒10:00-11:15 💻 Online Webinar
The Azure AI Agent Service allows you to build semi-autonomous software that can be given a goal and will work to achieve that goal without you knowing in advance exactly how it's going to do that or what steps it's going to take. This is a powerful tool for automating tasks and processes that are too complex to be easily automated with traditional software.
What sets Azure AI Agent Service apart?
In our experience talking to hundreds of organizations, we have learned that developing secure, reliable agents rapidly requires four primary ingredients:
Rapidly develop and automate processes: Agents need to seamlessly integrate with the right tools, systems and APIs to perform deterministic or non-deterministic actions.
Integrate with extensive memory and knowledge connectors: Agents need to manage conversation state and connect with internal and external knowledge sources to have the right context to complete a process.
Flexible model choice: Agents built with the appropriate model for its task can enable better integration of information from multiple data types, yield better results for task-specific scenarios, and improve cost efficiencies in scaled agent deployments.
Built-in enterprise readiness: Agents need to be able to support an organization's unique data privacy and compliance needs, scale with an organization's needs, and complete tasks reliably and with high quality.
Learning Outcomes:
👨🏻💻Understand the Azure AI Agent Service
👩🏻💻Understand Azure OpenAI Chat Completion Function Calling
👨🏻💻Learn how to build conversational agents
🕒11:15-12:30 🎓Expert Hour
Q&A session with Ofir Natan
Introduction to RAG: Enhancing AI Apps with Azure AI Search
📅April 8th 🕒10:00-11:15 💻 Online Webinar
Learn how to build a production-ready Retrieval Augmented Generation (RAG) application to chat over your domain's data with Azure AI Search. Discover the benefits of hybrid search with semantic ranker to find both vector and keyword-based results amongst billions of documents. Explore different approaches to data ingestion, to extract, split, vectorize, and store your data in Azure AI Search. Consider multiple ways to evaluate your RAG app answers, to ensure high-quality responses. Finally, see how you can productionize your RAG app with efficient vector storage, private network deployment, and user authentication.
Learning Outcomes:
👩🏻💻Basics of vector embeddings and vector search strategies
👨🏻💻Azure AI Search option: full-text search, vector search, hybrid search, semantic ranker
👩🏻💻Data ingestion process for Azure AI Search, manual and integrated vectorization feature
👨🏻💻Evaluation strategies for RAG app answers: AI Foundry, Promptflow-evals SDK
👩🏻💻Efficient vector storage with quantization
👨🏻💻Security best practices: private network deployment, user authentication, data access control
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Yariv Winestein
Code-First GenAIOps From Prototype to Production
📅April 22nd 🕒10:00-11:15 💻 Online Webinar
In this session, we will demonstrate the development of an agentic creative assistant application leveraging state-of-the-art technologies such as Prompty, GPT-4o, GPT-3.5 Turbo, and FastAPI. The application is deployed to Azure Container Applications, utilizing azd for deployment, AppInsights for monitoring, and Promptflow traces for debugging and tracing. The session aims to highlight why Azure AI is the best platform for developing LLM-powered apps with robust end-to-end flow orchestration, tracing/debugging, and monitoring capabilities.
Learning Outcomes:
👩🏻💻Learn how Azure AI's code-first tooling, such as Prompty and Promptflow, can streamline and simplify the LLM lifecycle.
👨🏻💻Understand that GenAIOps requires non-linear, iterative processes.
👩🏻💻Learn the practicalities of deploying LLM powered applications to production
👨🏻💻Gain the ability to stay in their preferred local development environment when desired and smoothly switch to AI Foundry for enhanced collaboration.
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Lev Andelman
Choosing the Right Generative AI Model: LLMs, SLMs, and Beyond
📅April 29th 🕒10:00-11:15 💻 Online Webinar
Today, there are many Generative AI models to choose from: Large Language Models (LLMs), Small Language Models (SLMs), proprietary models, open models, models in the cloud, models on devices, text models, code models, image models, and multimodal models. In this session, we'll provide guidance to help you choose the right model to fit your needs, and tools you can use to evaluate and compare models for your specific tasks.
Learning Outcomes:
👨🏻💻Understanding of Generative AI Models: Attendees should leave with a clear understanding of what generative AI models are, how they work, and their significance in various applications.
👩🏻💻Model Selection Criteria: Participants will learn how to choose the right model for specific tasks based on factors such as task requirements, model capabilities, and performance metrics.
👨🏻💻Awareness of Model Types: We’ll explore different types of generative models, including Large Language Models (LLMs) like GPT-3, Small Language Models (SLMs), and multimodal models that handle text, code, and images.
👩🏻💻Fine-Tuning Techniques: Attendees will see how fine-tuning can improve model performance and adapt it to specific use cases.
👨🏻💻Evaluation and Comparison Tools: We’ll discuss industry-standard evaluation metrics and tools like Azure AI Foundry for accurate model measurement.
👩🏻💻Real-World Case Studies: Examples of successful model applications will provide insights into practical deployment scenarios.
👨🏻💻The Future of Generative AI: We’ll wrap up with thoughts on where this field is headed and its potential impact.
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Liana Ziskind
Practical Agentic AI: Building Multi-Agent Systems with AutoGen and MCP
📅May 6th 🕒10:00-11:15 💻 Online Webinar
In this session, we’ll dive into building multi-agent systems using AutoGen and MCP (Model Context Protocol). You’ll see how AutoGen’s asynchronous, event-driven architecture simplifies multi-agent workflows, and how MCP provides unified data access for richer, context-aware AI. Through live demos, you’ll learn practical techniques to prototype and scale collaborative AI solutions, unlocking smarter, more adaptive capabilities.
Learning Outcomes:
👩🏻💻 Understand the core concepts of AutoGen and MCP.
👨🏻💻 Observe how to build a simple multi-agent system using AutoGen.
👩🏻💻 See how agents can access real-time data using MCP.
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Avihai Hajaj
3rd In-Person Event - The Big MCP Hackathon!
📅May 12-14 🕒3 days event 🤝 Physical Event @ Microsoft Reactor Israel
Our 3rd and last in-person event of GeekAcademy will serve as a unique hackathon for AI builders focused on the Model Context Protocol (MCP) and agent-to-agent (A2A) collaboration.
The hackathon aims to build an AI application by combining MCP and A2A. What does that mean? You’ll be creating agents with memory, agents that can communicate with one another, tools with shared and continuous context, autonomous workflows, and prototypes that aren’t just reactive, but also coordinated. In this hackathon, you’ll build a real prototype based on the most advanced frameworks available today, guided by the women and men shaping the field.
In addition, you’ll gain early access to beta versions of cutting-edge tools and technologies. The most outstanding projects will be showcased in Microsoft's AI Tour event, taking place June 3rd, 2025 in Expo Tel Aviv and will be showcased within the global AI Tinkerers network, including Microsoft, AI21, and other leading companies in the AI world. This could be your launchpad — or even your foot in the door toward collaborations, funding, or a new role.
The hackathon is led by engineers and experts from Microsoft, AI21, and LlamaIndex, This three-day sprint will push the boundaries of AI-native applications.
👾 For developers with hands-on experience building AI systems.
🚀 Come with an idea — leave with a working prototype.
To participate in this event - registration for the course and an email approval is required, and a confirmation email after submitting the application form.
Build with Us: A Multi-Agent AI Solution on Azure OpenAI
📅May 13th 🕒10:00-11:15 💻 Online Webinar
In this workshop, attendees will be introduced to the concept of Agents, an approach in AI that combines thought and action using LLMs and tools to achieve a desired goal. The sample presented will demonstrates how to create a Python app that takes a topic and instruction from a user then calls a research agent that uses the Bing Search API to research the topic, a product agent that uses Azure AI Search to do a semantic similarity search for related products from a vector store, a writer agent to combine the research and product information into a helpful article, and an editor agent to refine the article that's finally presented to the user.
Learning Outcomes:
👩🏻💻Implement a real world LLM-basedd agent lifecycle Understand agents and prompt engineering with Prompty
👨🏻💻Utilize tracing for debugging and observability
👩🏻💻Build and run Contoso Creative Writer
👨🏻💻Set up automated evaluations with GitHub Actions
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Nir Marcu
Hacking Your Own AI: Red Teaming, Guardrails, and Live Attack Scenarios
📅May 20th 🕒10:00-11:15 💻 Online Webinar
Learn essential security practices for responsible generative AI deployment. We'll cover the AI risk landscape and key frameworks including MITRE Atlas, NIST AI, and OWASP for LLMs, alongside Microsoft's principles for trustworthy AI. Through strategic insights and live demonstrations, you'll see real-time AI attacks using the PyRIT framework to identify vulnerabilities before they can be exploited. This session provides practical security strategies for engineers, DevOps professionals, AI/MLOps practitioners, and technology leaders building secure AI systems.
Learning Outcomes:
👩🏻💻Identify Core AI Threats: Understand key risks - like prompt injection and data poisoning—that impact generative AI.
👨🏻💻Adopt Governance Frameworks: Apply MITRE Atlas, NIST, OWASP, and Microsoft’s Responsible AI to systematically manage AI risks.
👩🏻💻Leverage Red Teaming Tools: Use PyRIT for live attack simulations to uncover hidden AI vulnerabilities.
👨🏻💻Implement Robust Defenses: Protect AI systems with Azure AI Content Safety, Prompt Shields, and HiddenLayer.
🕒11:15-12:30 🎓Expert Hour
Q&A Session with Elli Shlomo
<Empowering your dev skills and organization business value with AI tooling from Microsoft& GitHub>
GeekAcademy is a comprehensive 3-month course designed to take developers on a deep dive into the world of AI. Whether you’re new to AI or looking to sharpen your skills, this course covers everything from foundational concepts to advanced solutions. Led by experts from Microsoft and GitHub, you'll explore the fundamentals of generative AI and gain hands-on experience using industry-leading tools like Azure AI Studio and GitHub Copilot in Visual Studio and VS Code. Learn essential prompting techniques and best practices for integrating AI into your development workflow.
Throughout the course, you’ll build real-world applications, from AI-powered agents to multi-tasking assistants, while gaining insights into cutting-edge models such as LLMs and SLMs. Explore diverse AI use cases across different industries, and understand how to tailor solutions for specific personas. With practical exercises and in-depth sessions, you’ll master code-first GenAIOps, taking prototypes to production seamlessly. By the end of the course, you’ll be equipped to innovate and build AI-driven applications, harnessing the full potential of Azure and GitHub tools to revolutionize your development projects.
<Speakers>
<Gallery>
<Partners>
The training course by Geektime and Microsoft is brought to you thanks to the support of our partners, who recognize the course and its students.
<Community Partners>
<Mentors>
<V.O.D>
GeekAcademy is part of Microsoft's national training program aimed at empoweringIsrael’s develope
r community with advanced AI tools. This initiative is designed to enhance and upgrade development skills through AI, pushing Israel’s high-tech industry to the forefront of global technological innovation. By equipping developers with cutting-edge tools and knowledge, the program fosters growth, expertise, and leadership in the rapidly evolving AI landscape, ensuring that the local tech community stays ahead in a competitive market.
AI SKILLS NAVIGATOR
Chart your course. Learn AI today.
Unlock new opportunities with AI skills that are in demand now and in the future. Use AI to find the learning path that's right for you.
GeekAcademy is brought to you by