Dr Bill Ayers is a consultant developer and solution architect who has been working with computers for over 30 years. He originally earned his PhD in applications of computers in engineering before specialising in collaboration with SharePoint and more recently Microsoft 365 and Azure. He also specialises in mobile development and agile software development practices, and has been doing AI since the 1990s. He is a Microsoft Certified Master and Charter MCSM for SharePoint, and a Microsoft Certified Trainer and Microsoft MVP for M365 and AI Platform. He has also taken over forty Microsoft certifications and is a CompTIA CTT+ certified classroom trainer. He speaks regularly at international conferences and user groups and is based in Sheffield, UK.
08/06/2026
Kompas Xnet
Ljubljana, Slovenia
08/06/2026
Kompas Xnet
Ljubljana, Slovenia
08/06/2026
Kompas Xnet
Ljubljana, Slovenia
05/05/2026
Confex - Koelncongress
Cologne, Germany
05/05/2026
Confex - Koelncongress
Cologne, Germany
08/06/2026, Kompas Xnet
Ljubljana, Slovenia
With the popularity of Chat-GPT and Copilots comes the inevitable speculation of where we are on the AI hype cycle. Are we dealing with "glorified statistics", or is there more to this? In this talk we'll look at the wiring under the board, and what really lies behind Large Language Models like GPT-4. After taking a broad look at Artificial Intelligence and Machine Learning, we'll look at principles like transfer learning, and transformer architectures. As well as the theory, we'll see how it's been applied to solving real problems. And we'll also try to get a feel for where the current AI models sit in relation to human intelligence. Finally, we'll look at the broader AI hype cycle, consider the ethical and existential risks in this rapidly moving field, and see how close we are to artificial general intelligence.
08/06/2026, Kompas Xnet
Ljubljana, Slovenia
Can Europe do AI? You have probably heard about "Le Chat", an AI chatbot similar in its functionality to ChatGPT or Claude.ai. But Mistral AI, the French company behind "Le Chat" has much more to offer, and at the moment, together with German DeepL, it is the best that Europe has to offer in the AI space. Also, Mistral AI is committed to open-source development and has released several models under open-source licenses, which makes it a competitor not only to Open AI and Anthropic, but also to DeepSeek and Meta's Llama. This will be a deep dive session into Mistral: it's capabilities, it's lovely French quirks, and how can you make use of it. In this session we will discuss: - Mistral AI basics - Hosting and consuming Mistral AI (Mistral APIs, Azure AI, self-hosting) - Using the Microsoft AI tech stack (Microsoft Agent Framework, Semantic Kernel and Microsoft AI Extensions) to work with Mistral AI - A real life example of using Mistral AI within product development for run.events Note: I am delivering this session on behalf of my good friend and fellow Microsoft Foundry MVP Adis Jugo. À bientôt!
08/06/2026, Kompas Xnet
Ljubljana, Slovenia
GitHub has significantly enhanced its Copilot offering with the release of agent mode. This feature streamlines and automates code editing workflows, allowing developers to iterate on code changes more efficiently using natural language prompts. Agent mode takes GitHub Copilot even further by enabling Copilot to autonomously plan and execute tasks, including suggesting and running terminal commands, and iterating to resolve issues. These advancements signify a move towards a more "agentic AI" that proactively assists developers throughout the development lifecycle. We'll be mainly using C# and TypeScript languages (not that it matters quite so much when you have an agent to worry about syntax!).
05/05/2026, Confex - Koelncongress
Cologne, Germany
In case you hadn't noticed, Large Language Models tend to start making up stories when they run out of facts. There are a few reasons for this, but a lot of it is because they are just generating 'completions'. They don't stop just because they've run out of ideas (and yes, we all know actual people who do that as well). They've also been trained to be 'helpful', so you might have detected a certain tone in generated text. I'm pretty sure we can recognise GPT-4 output in the same way all those DALL-E images have a certain look. In this talk we'll examine the reasons for this behaviour. And more importantly we'll see how to use techniques like RAG and prompt engineering to mitigate these issues, and how to use a more complex 'multi-agent' architecture to build reliable AI solutions. We'll illustrate these techniques by looking at some real-life applications that use these techniques.
05/05/2026, Confex - Koelncongress
Cologne, Germany
As AI continues to power new breakthroughs, how can innovation be balanced with responsibility? This panel explores the role of ethics in AI product design and development, examining case studies from startups, tech companies, and research labs. Panelists will discuss practical approaches to embedding responsible AI principles into design workflows, the challenges of aligning business incentives with ethical outcomes, and how to measure the real-world impact of AI systems.
30/03/2026, Congress Center Hotel Hills
Ilidža, Bosnia and Herzegovina
Large language models have been a game changer, but they have their limitations. They only know what was generally available up to the point they were trained. They don't have access to recent events, or your own private data. What's worse, if you ask them about something they don't know about, they start making stuff up! That's why we need to build more sophisticated solutions that combine different models, add some prompt engineering and RAG (Retrieval Augmented Generation), as well as some custom code or plugins, and then a few more layers of safety and responsible AI checks. When you want to combine multiple skills and perform tasks to achieve an objective, you can use Agent Framework to handle all the low-level details of handling LLMs. Microsoft Agent Framework is an SDK, available in C#, Python and Java. In this talk, we'll focus on the C# version and build enterprise solutions with .NET. You'll see how we can use it to build an "agent", that goes beyond text responses and that actually does something.
30/03/2026, Congress Center Hotel Hills
Ilidža, Bosnia and Herzegovina
As AI continues to power new breakthroughs, how can innovation be balanced with responsibility? This panel explores the role of ethics in AI product design and development, examining case studies from startups, tech companies, and research labs. Panelists will discuss practical approaches to embedding responsible AI principles into design workflows, the challenges of aligning business incentives with ethical outcomes, and how to measure the real-world impact of AI systems.
30/03/2026, Congress Center Hotel Hills
Ilidža, Bosnia and Herzegovina
Large Language Models (LLMs) have transformed the way we build intelligent applications, but using them effectively requires more than just good prompts. Out of the box, LLMs are frozen in time, lack access to your private data and, most worryingly, can produce plausible but incorrect responses. To create trustworthy AI agents - applications that can reason and act - we need to combine models with additional tools, data sources, and orchestration layers. This one-day course will guide you through using Azure AI Foundry, Microsoft's one-stop portal for AI infrastructure. We'll use AI frameworks to build practical AI applications, including agentic systems that can plan, reason, and act on objectives. We’ll see how to extend raw LLM capabilities with techniques such as prompt engineering, Retrieval Augmented Generation (RAG), plugins (tools), and orchestration. This hands-on, full-day course will use various AI models provisioned in Azure AI Foundry. We'll focus on Microsoft Agent Framework, an AI orchestration SDK available in C# and Python that simplifies the integration of LLMs into enterprise-grade solutions. You'll learn how to: • Apply prompt engineering and RAG for accuracy and grounding. • Extend LLMs with custom plugins, APIs, and business logic. • Build multi-agent workflows. • Use responsible AI practices. • Design and deploy agentic systems that go beyond text generation to perform actions. Bring your laptop to follow along with the examples, or simply observe and learn. Either way, you’ll be equipped to design, build, and deploy AI applications that go beyond chat and deliver real business value.
25/10/2025, Lisbon
Lisbon, Portugal
Extending Microsoft 365 Copilot is a great way of getting your custom applications in the hands of business users, because you're making it available right where they're working. But there's quite a bit of setup involved in getting up and running - or rather there was. Using Teams Toolkit we can quickly get a Copilot Custom Engine Agent built and delivering awesomeness, because the tooling does all the heavy configuration, leaving us to focus on what we do best - code!
24/09/2025, National Museum Of Computing
Milton Keynes, United Kingdom
In case you hadn't noticed, Large Language Models tend to start making up stories when they run out of facts. There are a few reasons for this, but a lot of it is because they are just generating 'completions'. They don't stop just because they've run out of ideas (and yes, we all know actual people who do that as well). They've also been trained to be 'helpful', so you might have detected a certain tone in generated text. I'm pretty sure we can recognise GPT-4 output in the same way all those DALL-E images have a certain look. In this talk we'll examine the reasons for this behaviour. And more importantly we'll see how to use techniques like RAG and prompt engineering to mitigate these issues, and how to use a more complex 'multi-agent' architecture to build reliable AI solutions. We'll illustrate these techniques by looking at some real-life applications that use these techniques.
21/06/2025, Van der Valk Hotel, Vianen
Vianen, Netherlands
You might have looked at custom Copilots, and RAG (Retrieval Augmented Generation), but sometimes you need more. You need to build an “agent”, an AI model that can combine multiple skills and perform tasks to achieve an objective. There are a few tools for doing that, like LangChain and Semantic Kernel. In this talk, we’ll focus on the latter, which is ideally suited to work with the Microsoft technology stack, and the technology that lies behind many of the Copilots offered as part of Microsoft 365. In this talk, we’ll look at the different options for building AI agents that go beyond RAG and Plugins and can perform complex processes. And we’ll see how to use Semantic Kernel to go beyond generating text by combining large language models with other tasks like calling APIs and executing processes. We'll build sophisticated solutions that use context memory, function-calling, and look at multi-agent solutions.
21/06/2025, Van der Valk Hotel, Vianen
Vianen, Netherlands
Join us for a candid and entertaining panel on AI. This isn’t your typical AI session—no sales pitches or marketing fluff. Instead, we’re sharing real-life stories of how AI tools like Copilot, and others assist us in both our professional tasks and personal lives. We’ll discuss the practical ways AI integrates into our daily routines. Expect honest conversations about the successes, the hiccups, and the humorous moments that come with relying on AI. Whether you’re an AI enthusiast or just curious about its everyday applications, this session offers relatable insights and a few laughs along the way. Come and discover how AI is not just a futuristic concept but a present-day companion in our work and personal lives.
02/06/2025, Kompas Xnet
Ljubljana, Slovenia
Large language models have been a game changer, but they have their limitations. They only know what was generally available up to the point they were trained. They don't have access to recent events, or your own private data. What's worse, if you ask them about something they don't know about, they start making stuff up! That's why we need to build more sophisticated solutions that combine different models, add some prompt engineering and RAG (Retrieval Augmented Generation), as well as some custom code or plugins, and then a few more layers of safety and responsible AI checks. When you want to combine multiple skills and perform tasks to achieve an objective, you can use Semantic Kernel to handle all the low-level details of handling LLMs. Semantic Kernel is an SDK, available in C#, Python and Java. In this talk, we'll focus on the C# version and build enterprise solutions with .NET. You'll see how we can use it to build an "agent", that goes beyond text responses and that actually does something.
02/06/2025, Kompas Xnet
Ljubljana, Slovenia
In case you hadn't noticed, Large Language Models tend to start making up stories when they run out of facts. There are a few reasons for this, but a lot of it is because they are just generating 'completions'. They don't stop just because they've run out of ideas (and yes, we all know actual people who do that as well). They've also been trained to be 'helpful', so you might have detected a certain tone in generated text. I'm pretty sure we can recognise GPT-4 output in the same way all those DALL-E images have a certain look. In this talk we'll examine the reasons for this behaviour. And more importantly we'll see how to use techniques like RAG and prompt engineering to mitigate these issues, and how to use a more complex 'multi-agent' architecture to build reliable AI solutions. We'll illustrate these techniques by looking at some real-life applications that use these techniques.
02/06/2025, Kompas Xnet
Ljubljana, Slovenia
Extending Microsoft 365 Copilot is a great way of getting your custom applications in the hands of business users, because you're making it available right where they're working. But there's quite a bit of setup involved in getting up and running - or rather there was. Using Teams Toolkit we can quickly get a Copilot Custom Engine Agent built and delivering awesomeness, because the tooling does all the heavy configuration, leaving us to focus on what we do best - code!
26/05/2025, Congress Center Düsseldorf
Düsseldorf, Germany
As Europe continues to develop its own technological ecosystem, enterprises face critical decisions regarding the adoption of European tech solutions. From cloud infrastructure and AI to cybersecurity and enterprise software, European technology offers unique advantages such as strong data protection, compliance with EU regulations, and reduced reliance on foreign providers. However, challenges remain, including market fragmentation, scalability concerns, and competition with dominant US and Chinese tech firms. This panel will explore the real-world potential of European tech in enterprise environments, examining the benefits, risks, and strategic considerations for businesses looking to integrate homegrown solutions. Industry leaders, policymakers, and tech experts will discuss how European enterprises can leverage local innovation while maintaining global competitiveness.
26/05/2025, Congress Center Düsseldorf
Düsseldorf, Germany
With the popularity of Chat-GPT and Copilots comes the inevitable speculation of where we are on the AI hype cycle. Are we dealing with "glorified statistics", or is there more to this? In this talk we'll look at the wiring under the board, and what really lies behind Large Language Models like GPT-4. After taking a broad look at Artificial Intelligence and Machine Learning, we'll look at principles like transfer learning, and transformer architectures. As well as the theory, we'll see how it's been applied to solving real problems. And we'll also try to get a feel for where the current AI models sit in relation to human intelligence. Finally, we'll look at the broader AI hype cycle, consider the ethical and existential risks in this rapidly moving field, and see how close we are to artificial general intelligence.
26/05/2025, Congress Center Düsseldorf
Düsseldorf, Germany
In this intense session I'll show you six ways you can deliver a huge amount of business benefit to almost any organization with a moderate amount of development effort. In a series of quick-fire demos, we'll look at Office Add-ins for Word, Excel, PowerPoint and Outlook, as well as extensions for SharePoint and Teams. We'll also see how we can use the Microsoft Graph and AI to take the intelligence behind the entire Microsoft 365 platform and deliver it where business users spend their working day. Wouldn't you like to be the hero that lets your users work faster, suffer less information overload, and see their families again?
09/01/2025, UA 92, Manchester
MANCHESTER , United Kingdom
Following successful and popular Sara’s session from the past Summit, we want to bring this interesting topic in Manchester as well! More than often trainers compare MCT program with MVP program just to conclude both programs are drastically different. Or are they? MCTs possess some unique skills that can be useful to become members of both programs! In this session you will have a chance to meet MCTs who are also MVPs and we’ll cover: • What the MVP program is (and what it is not) • What the MVP Communities is and what programs it includes • How to become an MVP • and more… Bring your questions to the session – we need them! – as it is an interactive session and suitable for all!
09/01/2025, UA 92, Manchester
MANCHESTER , United Kingdom
This talk will provide Microsoft Certified Trainers with the knowledge and tools necessary to effectively teach the intricacies of the Microsoft AI platform. You will gain an understanding of the core concepts and capabilities of the Microsoft AI platform at the fundamentals level, including Azure AI Services and Azure Machine Learning. We'll then look at the associate-level training and courses for Azure AI Engineer and Azure Data Scientist. We'll also review some of the relevant Applied Skills learning paths and assessments.
25/09/2024, The National Museum of Computing
Bletchley, United Kingdom
In the world of hybrid work, it's so much harder to keep people connected and working together. You need to prepare the ground, and then nurture your corporate culture. That's why we have Viva Connections - a branded company portal inside Microsoft Teams, along with a mobile-optimized solution for frontline workers and information workers on the go. Let's see what's involved in setting up Viva Connections and adding it to Teams. Then we'll see how to customise the mobile dashboard. Finally, we'll go into developer mode, and add our own dashboard cards to give employees quick access to critical content and the tools to get things done.
01/06/2024, Van der Valk Hotel, Vianen
Vianen, Netherlands
Everybody's heard about ChatGPT, based on the latest GPT-3.5 AI models for text processing. With its human-like and school homework friendly text generation, you might be wondering what it all means, and where it's all going. Who or what is OpenAI, and why is Microsoft investing so heavily in it? And how will Microsoft 365 Copilot affect the world of business collaboration and communication? In this overview we'll see how natural language processing (NLP) has changed in the last few years, especially with the latest generative models based on transformers trained on mind-bogglingly large datasets. And I'll answer the question of whether ChatGPT is sentient, or likely to be in the future. I'll lift the curtain and show you what's really going on behind the scenes. Don't worry if AI is still all a bit of a mystery. For this talk, attention is all you need.
20/05/2024, Kompas Xnet
Ljubljana, Slovenia
Microsoft 365 Copilot is great! But if you have more specific or vertical industry needs, you probably want to build something more specialized. In this talk, we'll see how to go about building your own Copilot application for your business. We'll look at some of the practical details of using AI to build intelligent assistants. Contrary to what you might think, it doesn't actually make practical sense to throw everything at the latest (and most expensive) large language models. We need to use a number of techniques, like prompt engineering, RAG, semantic search, fine tuning, small or specialized language models, and some custom logic. And then we need to orchestrate all these components with tools like LangChain or Semantic Kernel. But what to use where? That's the skill that makes the difference between success and failure, and it's a bit of a black art. Welcome to the inner circle!
20/05/2024, Kompas Xnet
Ljubljana, Slovenia
You can use your existing knowledge of JavaScript, HTML5, CSS, and perhaps jQuery to build client-side web applications. You can also use the same technology to build solutions for Android, iOS, Windows 11, and Microsoft 365. To get the best performance out of web technology you need to use one of the JavaScript frameworks for client-side development. In this talk, we'll focus on ReactJS, and look at the design principles behind React - not just how it works, but why. We'll help you decide if React is the right tool for you, and how to get the most out of it.
14/05/2024, Rheinmain Congresscenter
Wiesbaden, Germany
In recent past, we witnessed astonishing rise of AI but what comes next? Rapid development in this filed is ongoing but there are many challenges and questions. This panel brings together experts and visionaries from diverse fields within AI to explore emerging trends, anticipate breakthroughs, and address pressing questions surrounding ethics, regulation, and societal implications. Join us as we navigate the frontier of AI innovation and envision the possibilities that lie beyond the horizon.
14/05/2024, Rheinmain Congresscenter
Wiesbaden, Germany
Everybody's heard about ChatGPT, based on the latest GPT-3.5 AI models for text processing. With its human-like and school homework friendly text generation, you might be wondering what it all means, and where it's all going. Who or what is OpenAI, and why is Microsoft investing so heavily in it? And how will Microsoft 365 Copilot affect the world of business collaboration and communication? In this overview we'll see how natural language processing (NLP) has changed in the last few years, especially with the latest generative models based on transformers trained on mind-bogglingly large datasets. And I'll answer the question of whether ChatGPT is sentient, or likely to be in the future. I'll lift the curtain and show you what's really going on behind the scenes. Don't worry if AI is still all a bit of a mystery. For this talk, attention is all you need.
14/05/2024, Rheinmain Congresscenter
Wiesbaden, Germany
With distributed workforces, remote working, and disembodied meetings, organizations are struggling to keep their people engaged as part of a team. Viva Connections is designed to be your company portal, as an intranet, as a component of Teams on the desktop, and critically for frontline workers who primarily interact with Teams on a mobile device. Adaptive Card Extensions (ACEs) are a Teams extension point for the Viva Connections dashboard, that allows you to surface your organization's data in a way that is flexible and inclusive. We'll look at the thinking behind Adaptive Cards, the Home Site dashboard, and see how we can use that to build simple but effective reference points for both desktop users and workers on the go.
09/04/2024, Irving Convention Center at Las Colinas
Irving, United States of America
This speculative session will explore the need, the opportunity and what it might take to create your personal AI, your doppelganger if you will. It will touch on ethics and intellectual property.
09/04/2024, Irving Convention Center at Las Colinas
Irving, United States of America
Everybody's heard about ChatGPT, based on the latest GPT-3 AI models for text processing. With its human-like and school homework friendly text generation, you might be wondering what it all means, and where it's all going. Who or what is OpenAI, and why is Microsoft investing so heavily in it? And how will it affect the world of business collaboration and communication? In this quick overview we'll see how natural language processing has changed in the last few years, especially with the latest generative models based on transformers trained on mind-bogglingly large datasets. And I'll answer the question of whether ChatGPT is sentient, or likely to be in the future. I'll lift the curtain and show you what's really going on behind the scenes. Don't worry if AI is still all a bit of a mystery. For this talk, attention is all you need.
27/09/2023, National Museum Of Computing
Milton Keynes, United Kingdom
Artificial Intelligence and Machine Learning are popular topics at the moment, but how much of it is hype, and can AI deliver tangible business benefits? We can use the pre-trained models in Azure Cognitive Services to identify well-known objects and landmarks, but that's a narrow field that's the result of huge research projects and ingesting massive amounts of data. How can we apply that to practical business problems, like visually detecting faults, spotting our company logo, or answering emails? To understand the answer to this question you need to understand the principle of Transfer Learning. We'll look at the theory, and then see it working, and see some of the tools in Azure Cognitive Services and other toolkits that allow us to use this technique without needing to be an expert in AI. Then we'll look at Transformers, a newer technology that has made a huge impact recently with autogenerative language models that are used by Chat-GPT and Copilot. And we'll talk about where this technology is taking us, and realistically look at the ethical and existential risks in this rapidly moving field.
01/09/2023, Didin Konak Kopačevo
Kopačevo, Croatia
Artificial Intelligence and Machine Learning are popular topics at the moment, but how much of it is hype, and can AI deliver tangible business benefits? We can use the pre-trained models in Azure Cognitive Services to identify well-known objects and landmarks, but that's a narrow field that's the result of huge research projects and ingesting massive amounts of data. How can we apply that to practical business problems, like visually detecting faults, spotting our company logo, or our competitor's products on shelves? To understand the answer to this question you need to understand the principle of Transfer Learning. We'll look at the theory, and then see it working, and see some of the tools in Azure Cognitive Services and other toolkits that allow us to use this technique without needing to be an expert in AI, or even being able to code. Then we'll look at some of the latest developments in large language models using transformers. Finally, we'll consider the ethical and existential risks of AI.
10/06/2023, Van der Valk Hotel, Vianen
Vianen, Netherlands
Getting started with Teams development isn't so easy - so many extension points, so many things to set up, reverse proxies, JavaScript frameworks, app registration; it can all seem a bit overwhelming. In this session I'll show how you can get up and running fast with the Teams Toolkit, which is available for Visual Studio Code as well as the Visual Studio IDE, and also from the command line. Open up an infinity of possibilities for crafting business solutions by making the transition from no-code to low-code to pro-code! And let Teams Toolkit smooth out the rough edges and get you building solutions.
22/05/2023, Congress Center Düsseldorf
Düsseldorf, Germany
Getting started with Teams development isn't so easy - so many extension points, so many things to set up, reverse proxies, JavaScript frameworks, app registration; it can all seem a bit overwhelming. In this session I'll show how you can get up and running fast with the Teams Toolkit, which is available for Visual Studio Code as well as the Visual Studio IDE, and also from the command line. Open up an infinity of possibilities for crafting business solutions by making the transition from no-code to low-code to pro-code! And let Teams Toolkit smooth out the rough edges and get you building solutions.
20/05/2023, Novotel Milano Nord Ca Granda
Milan, Italy
If you've looked at some of the low-code options in Microsoft 365, it might have whet your appetite for some full-on development. But how do you get started with Teams development ? So many extension points, so many things to set up, reverse proxies, JavaScript frameworks, app registration; it can all seem a bit overwhelming. In this session I'll show how you can get up and running fast with the Teams Toolkit, which is available for Visual Studio Code as well as the Visual Studio IDE, and also from the command line. Open up an infinity of possibilities for crafting business solutions by making the transition from no-code to low-code to pro-code! And let Teams Toolkit smooth out the rough edges and get you building solutions.
05/10/2022, National Museum Of Computing
Milton Keynes, United Kingdom
Azure Cognitive Services are great, but you need a reliable network connection to the cloud, right? Wrong! For one thing, there's an increasing number of services that can be deployed to containers. If you don't have a reliable network connection, or have limited bandwidth, or if you have data that's needs to be kept on-premises, these are all use-cases for deploying Azure Cognitive Services to containers. We can also use Azure IoT Hub and IoT Edge to manage devices and services. A second option is to export a custom trained model. We'll see how to use Custom Vision in Azure Cognitive Services to train a custom computer vision model and export it as a TensorFlow model, and then deploy it to a Raspberry Pi Zero single board computer. Either way, you get the advantages of Azure Cognitive Services, but running outside Azure!