The Critical Four: Securing Agentic AI with the OWASP Top Risks

Agentic AI systems don’t just generate responses — they take actions, call tools, move data, and influence other agents. With this new autonomy comes a new attack surface. OWASP’s 2026 Top 10 for Agentic Applications is the first global framework for securing autonomous AI agents. In this session, we’ll focus on the Critical Four — the four risks that account for most real‑world incidents today: Agent Goal Hijack, Tool Misuse, Identity & Privilege Abuse, and Memory Poisoning. You’ll learn how attackers exploit them, why traditional guardrails fail, and practical mitigations you can apply immediately. If you’re building, deploying, or securing AI agents, this session will show you where the real dangers are — and how to defend against them.”

Say what? You can run your .NET workloads on AWS???

When you think of .NET/dotnet core you most likely would not think of AWS, but you will be presently surprised to discover how much support Amazon has for .NET/dotnet core on AWS.

In this session we will go through some fundamentals of AWS including the tools & integration that AWS provides for VS and VSCode, We will then deploy .NET applications on AWS finally we will use AWS Cloud Native services monitor, build and deploy containerized applications.

Topics covered listed contains:

1. Using the AWS Toolkits
2. Deploy .NET Apps on AWS
3. Developing .NET Core Applications Using DynamoDB
4. Adding innovation with AI/ML
5. How to secure my .NET application on AWS
6. Using AWS X-Ray in .NET Applications
7. How to monitor my applications
8. Storing and Caching Data in DynamoDB
9. Integrate Amazon Cognito with .NET Core ASP.NET MVC Application
10. How to set up my CI/CD pipeline
11. Infrastructure Automation

Just enough Machine Learning to sprinkle onto your applications.

AI and machine learning is such a large topic and most of the time developers feel intimidated by the all the domain specific language they use (Regression, Hyper parameter, Sigmoid function, Random Cut Forest, K-means, etc, etc). Sounds complex!!!

In this session I will try to demystify some of the machine learning principles and at the end you will have some basics of AIML. I will also showcase how you can use some of the AIML services that you can sprinkle onto your applications to make them smarter.

Empower Your AI: Crafting a Custom Copilot with Semantic Kernel

Now that you have master prompt engineering, whats next?
In this talk we will go over a MIcrosoft Open Source solution called Semantic Kernel SDK, where it allows us to enhance your prompt and build your own solution of Copliot within your application. Concepts incude:
- Planner
- Memories
- Connectors
- Custom Plugins

In the session we will live code using SK to build our own plugin (skills) while getting an overview of the core concepts of SK such as memories, connectors, and kernels, before diving deeper into the new face of AI, which integrates LLM AI capabilities directly into applications. So come join me and lets build our own copilot to the next level with all the Lego blocks of building our next generation applications.

8 Cloud Design Patterns you ought to know.

In software engineering, a design pattern is a general repeatable solution to a commonly occurring problem in software design.
You probably know about the GoF patterns, but did you know there are also Cloud Design Patterns solutions to a commonly occurring problem when building applications in the Cloud.

In this Talk we will go through 8 Cloud Design Patterns that will help you in your Design and Implementation, Data Management, Resiliency and Security; namely

- External Configuration
- Cache Aside
- Federated Identity
- Valet Key
- Gatekeeper
- Circuit Breaker
- Retry
- Strangler

7 key concepts to build a secure cloud architecture

In this sessoin we will discusses the significance of creating secure cloud infrastructure as developers, security and operations teams transfer their assets to the cloud. Seven crucial concepts must be incorporated into a secure cloud architecture, and the session will provide a comprehensive examination of each concept to assist you in considering cloud security design in a practical and consistent manner.

The learning objectives include gaining knowledge of core cloud security architecture principles, obtaining a solid understanding of how to construct secure infrastructure for PaaS and IaaS deployments, and examining security examples from Microsoft Azure.

Target Aud: Developers, DevOps, Cloud Architects, Security Professionals

The Critical Five: Securing Your Agentic AI Applications

Agentic AI systems don’t just predict — they act. They plan, reason, call tools, move data, and trigger workflows autonomously. With that autonomy comes a radically expanded attack surface. Based on the OWASP Top 10 for Agentic Applications (2026), this session dives deep into five of the most critical and consistently exploited risks facing modern agentic architectures.
In this technical session, you’ll learn how attackers subvert autonomous behavior, chain multi‑step exploit paths, and weaponize the very capabilities that make agentic systems powerful. Through real‑world examples, architectural breakdowns, and practical mitigation strategies, you’ll leave with a concrete blueprint for securing your own agentic applications.

Unleash the Power: Crafting Agentic AI .NET Apps with Autogen Framework

Dive into the future of AI-driven development with Autogen Framework, an open-source tool that revolutionizes how we build complex workflows using conversational agents and patterns. In this demo-ful session, we’ll explore the fundamental concepts and conversational patterns essential for crafting multi-agent AI applications within the .NET ecosystem.

The session will try to help you to build a robust understanding of how to leverage large language models (LLMs) to orchestrate sophisticated, agentic workflows. Topic covered:

Core Concepts: Get to grips with the foundational elements of the Autogen Framework.

Conversational Patterns: Learn how to design and implement effective conversational agents that can collaborate seamlessly.

Practical Applications: Walk through real-world scenarios and use cases to understand the framework's potential.

Unleashing the Power of Vector Search with Azure SQL Database

This talk and live demo will explore how to leverage the capabilities of Azure SQL Database to perform high-performance vector searches, enabling developers to build intelligent applications that can understand and retrieve data based on semantic similarity.

We'll walk through a practical example demonstrating how to set up and optimize vector search in Azure SQL Database. Attendees will learn about the underlying concepts of vector search, best practices for implementation, and real-world use cases that showcase the power of this technology.

Whether you're a seasoned developer or new to the world of AI and data search, this session will provide valuable insights and hands-on knowledge to help you harness the full potential of vector search in your applications. Don't miss this opportunity to stay ahead of the curve and revolutionize your data retrieval strategies with Azure SQL Database!

Multi-Agents with Autogen and Semantic Kernel

This workshop showcases autogen (0.4) by presenting a set of simple scripts that create different type of agents and interactions between them with the purpose of highlighting the main capabilities of the agentic framework.

Open AI service deployed with GPT-4o
Azure Container Apps Session Pool

Agents That Talk Back: MCP, ACP, A2A, Oh my!

In the evolving landscape of AI, agents are no longer isolated tools—they’re becoming collaborators. This session dives into how developers can build intelligent, interoperable agents using the Model Context Protocol (MCP), Action Calling Protocol (ACP), and Agent-to-Agent (A2A) communication patterns. Whether you're working in .NET or Python, you'll learn how to:

Use MCP to connect agents to real-time data, tools, and APIs with minimal integration overhead.
Leverage ACP to enable agents to invoke actions across services and platforms.
Implement A2A to allow agents to discover, negotiate, and collaborate with other agents—securely and asynchronously.
We’ll walk through live demos showing how to:

Build an MCP server in Python and .NET.
Register and invoke actions using ACP.
Create multi-agent workflows using A2A with Semantic Kernel and Autogen.
Expect practical code, real-world use cases, and a few laughs as we explore how to make your agents not just smarter—but social.

Protecting the I in my Identity

In today’s hyper-connected world, our personal identity is more than just a name or email—it’s a collection of digital footprints, credentials, and behaviors that define who we are online. With cyber threats evolving at lightning speed, protecting your identity is no longer optional—it’s essential.
The talk will explore:

The Modern Identity Landscape: How our data is spread across social media, cloud services, and everyday apps.
Common Threats to Your Identity: Phishing, credential theft, social engineering, and identity fraud.
The Role of Multi-Factor Authentication (MFA): Why passwords alone are not enough.
Privacy in the Age of AI: How generative AI and data scraping amplify risks.
Best Practices for Individuals: Strong password hygiene, secure browsing habits, and managing digital footprints.
Emerging Technologies for Protection: Passwordless authentication, zero-trust principles, and identity protection tools.
What “Protecting the I” Really Means: Building a zero trust mindset of security awareness and resilience.