AI Agents Unleashed: From Prompt Puzzles to Task Titans

As AI applications evolve, their increasing complexity poses challenges related to token allowances and prompt construction. To address this, the use of AI agents has emerged as a powerful approach. These agents autonomously make decisions in dynamic environments, akin to human assistants. Imagine an agent that not only books your vacation but also tailors recommendations based on your preferences, plans your itinerary, and even invites friends. In the workplace, agents can execute tasks like sending emails or managing calendars. Google's Astra and OpenAI's GPT-4o exemplify this trend.

In this talk I will explain through demonstration the merits of this approach and how we can use frameworks like Semantic Kernel and AutoGen to leverage this approach to break down complex tasks and allow AI to dynamically build applications from smaller pieces.

The How and Why of DevOps

DevOps is a set of principles aimed at helping organizations execute better and provide more value with greater efficiency. It does this by emphasizing that organizations constantly self evaluate according to The Three Ways and seeking to improve communication within and between teams. By doing this, organizations can look to improve process and culture enabling them to achieve greater maturity and autonomy.

While that all sounds great the truth is, for many organizations, DevOps represents a radical shift in the way they do things and has so many variations that finding their own path is very challenging. As a result, many merely look to automate various tasks or embrace techniques such as Infrastructure as Code or GitOps. While these are noble achievements, they represent but a sliver of the potential offered through the DevOps principles.

In this talk I will share techniques and strategies I have employed at organizations over the course of my career to help foster better communication and team efficiencies. This goes beyond automation and focuses on how organizations structure teams, how those teams communicate within themselves and with other teams. How the communication and structure within an organization impact the type of and quality of software that is attainable. And I will share various anti-patterns that can make it hard, if not impossible, to get value from a DevOps transformation.

My goal is for attendees to leave the talk armed with new perspectives and techniques they can use to start, accelerate, or course correct a DevOps transformation for their organization.

An Introduction to Kubernetes

Kubernetes has become the defacto tool for orchestrating containerized applications. It changes the way we view deploying and operating applications giving teams immense flexibility which automating many aspects. Yet, it remains difficult to learn and can seem quite foreign to those just getting started with it. In this talk, I will take you through the origins of the platforms, what problem it solves, and its basic concepts.

By the end attendees will understand:
- What is Kubernetes and where it came from?
- Core concepts of Pod, Ingress, Service, Deployment, Node, and Cluster
- How to use of YAML to define minimum state
- How applications are deployed and executed within Kubernetes

Kubernetes for beginners and all skills levels

Exploring Autism in Engineering: A Personal Journey

In the dynamic world of engineering, where creativity meets precision, the lens of autism offers a unique perspective—one that blends challenges with strengths. As a seasoned technology consultant with 20 years of experience I know firsthand how these traits can help and deter individuals in the field.

The goal of this talk is threefold. First, I aim to dispel stereotypes and myths surrounding autistic individuals. Second, I strive to educate people about Autism Spectrum Disorder (ASD) and highlight its distinctions from traditional Autism, Asperger’s, and ADHD. Finally, I want to promote inclusivity by empowering neurotypical individuals to better understand and support their friends on the spectrum

I have no background in the behavioral sciences, this talk is from my personal experience and gathered research.

Strengthening Azure Applications: Private Endpoints and Managed Identity

Security is paramount when building applications in Azure. It’s not just about protecting your code; it’s also about how your application interacts with Azure services. In this session, we’ll explore two critical elements that can fortify your app’s defenses: Managed Identity and Private Endpoints.

Managed Identity acts as a trustworthy sidekick for your application, allowing secure authentication with Azure services without exposing secrets in your code. We’ll explore different flavors of Managed Identity—Managed, Unmanaged, and User-Managed—and discuss their optimal use cases. Meanwhile, Private Endpoints function like velvet ropes and bouncers, creating private network connections between your app and Azure services to keep unauthorized access at bay. We’ll delve into scenarios where Private Endpoints shine, such as meeting HIPAA or PCI DSS requirements, and demystify how Azure networking fits into the picture.

Unleashing the Power of Azure AI Search: Building Intelligent Applications

The backbone of intelligent applications, Azure AI Search offers contextual understanding, personalization, efficiency, and scalability. It goes beyond keyword matching by leveraging AI to comprehend data entities, sentiment, and relationships. Tailoring search results based on user behavior and optimizing performance, it effortlessly scales to handle large document volumes.

This workshop will offer a practical hands-on section where we’ll delve into practical scenarios using Azure AI Search. Participants will explore AI Cognitive Skills for transforming raw data, create custom web endpoints to enhance data processing, seamlessly integrate Azure OpenAI ChatGPT for conversational search interfaces, and learn pipeline debugging techniques.

After completing the workshop attendees will be able to create an Azure Search instance and leverage enrichment techniques to allow other applications, including AI, to use their applications more effectively.