M365.FM - Modern work, security, and productivity with Microsoft 365

Copilot Studio, AI Agents, RAG, and the Future of Business Automation with Nilüfer Doğan [MVP]

52 min · 27 jun 2026
aflevering Copilot Studio, AI Agents, RAG, and the Future of Business Automation with Nilüfer Doğan [MVP] artwork

Beschrijving

Artificial Intelligence is entering a new era. While chatbots introduced many organizations to generative AI, today's intelligent AI agents are capable of much more. They can retrieve enterprise knowledge, execute business processes, automate repetitive tasks, integrate with business systems, and support employees across departments. Microsoft is investing heavily in this vision through Copilot Studio, Azure AI Foundry, Azure OpenAI, Power Platform, and Azure AI Search.In this episode of M365 FM, Mirko Peters welcomes Microsoft MVP Nilüfer Doğan to explore how organizations can move beyond AI experiments and begin building production-ready enterprise AI solutions. FROM ECONOMICS TO MICROSOFT AI DEVELOPMENT Nilüfer shares her unique career journey from studying economics to becoming a Microsoft MVP and Platform Developer working with some of Microsoft's newest AI technologies.She explains how her analytical background helped shape the way she approaches software development, problem solving, automation, and enterprise architecture. Rather than following a traditional computer science path, she discovered Power Platform after initially working in Data Science before transitioning into low-code development.Her story demonstrates that successful AI professionals often combine technical expertise with business thinking. WHAT A MODERN POWER PLATFORM DEVELOPER REALLY DOES Many people imagine Power Platform developers simply building Power Apps or Power Automate flows.Nilüfer explains that today's role is much broader.Her daily work includes: * Building enterprise AI agents * Developing Power Platform solutions * Supporting digital transformation projects * Mentoring citizen developers * Integrating Azure AI services * Designing secure enterprise architectures Modern Power Platform professionals increasingly work across multiple Microsoft technologies instead of focusing on a single product. WHY COPILOT STUDIO IS NO LONGER "JUST A CHATBOT" One of the biggest myths surrounding Copilot Studio is that it simply replaces traditional chatbots.During the conversation, Nilüfer explains why that assumption is outdated.Today's Copilot Studio enables organizations to create intelligent AI agents capable of: * Using enterprise knowledge * Calling business systems * Executing workflows * Using multiple tools * Connecting to Microsoft 365 * Working with Azure AI services * Supporting complex business processes Instead of predefined conversation trees, modern AI agents reason over instructions and available tools. THE BIGGEST MISCONCEPTIONS ABOUT AI AGENTS Organizations often expect AI agents to solve every business problem.Nilüfer explains that this is one of the largest mistakes companies make.Not every problem requires an AI agent.Sometimes the correct solution is: * Power Apps * Power Automate * Power Pages * Traditional automation * Custom Azure development Choosing the correct Microsoft technology is often more important than using the newest AI feature. HOW COPILOT STUDIO HAS EVOLVED Microsoft has dramatically expanded Copilot Studio during the past year.The discussion explores how the platform has shifted from manually building conversation topics toward instruction-based AI development.Rather than configuring every response individually, developers increasingly focus on: * Better instructions * Better prompts * Better knowledge * Better tools * Better orchestration This changes the role of developers from conversation designers into AI solution architects. AI AGENTS VS TRADITIONAL CHATBOTS One of the most valuable parts of the conversation focuses on the difference between classic chatbots and modern AI agents.Traditional chatbots require developers to define every possible decision path manually.AI agents instead: * Understand user intent * Choose appropriate tools * Retrieve relevant information * Execute workflows * Generate contextual responses This represents one of the biggest shifts in enterprise automation over the past decade. WHEN TO USE COPILOT STUDIO — AND WHEN TO USE AZURE AI Every organization eventually asks the same question:Should we build this inside Copilot Studio or inside Azure?Nilüfer explains that there is no universal answer.Smaller business scenarios can often be solved entirely inside Copilot Studio.Larger enterprise solutions involving huge datasets, complex AI pipelines, or advanced retrieval usually benefit from Azure AI services including Azure AI Foundry and Azure AI Search. BUILDING A REAL ENTERPRISE AI SOLUTION Instead of discussing theory, Nilüfer shares a real customer scenario.She explains how she built an intelligent knowledge assistant connected to an on-premises Confluence environment.The solution included: * Document indexing * Permission-aware search * Azure AI Search * Enterprise authentication * Copilot Studio * Secure knowledge retrieval Users only receive information they are authorized to access, demonstrating why enterprise AI requires much more than simply uploading documents into an LLM. UNDERSTANDING AZURE AI SEARCH Azure AI Search plays a critical role in enterprise AI architectures.Nilüfer explains how indexing, vectorization, and semantic search dramatically improve both response quality and performance.Instead of searching thousands of complete documents every time a question is asked, Azure AI Search retrieves only the most relevant information before sending it to the language model.This reduces latency while improving answer quality. WHAT RAG REALLY MEANS Retrieval Augmented Generation (RAG) has become one of the most frequently discussed AI concepts.During the episode, Nilüfer explains the complete RAG pipeline in practical terms.Topics include: * Document chunking * Vector embeddings * Index creation * Knowledge retrieval * Large Language Models * Response generation Understanding these building blocks helps organizations create more reliable AI solutions while reducing hallucinations. MEASURING BUSINESS VALUE One challenge facing almost every AI project is proving business value.Nilüfer explains several approaches for measuring success beyond simple usage statistics.Organizations should evaluate: * Productivity improvements * Time savings * Conversation quality * User adoption * Return on investment * Automation success rates * Operational KPIs Copilot Studio analytics combined with business metrics provide a much clearer picture of AI adoption. GOVERNANCE CANNOT BE AN AFTERTHOUGHT Innovation often receives the most attention, but governance determines whether AI projects remain sustainable.The discussion explores why organizations need: * Development environments * Sandbox environments * Data Loss Prevention policies * Security controls * AI monitoring * Lifecycle management * Permission management Without governance, enterprise AI quickly becomes difficult to manage. SUPPORTING CITIZEN DEVELOPERS Citizen developers play an increasingly important role inside Microsoft Power Platform.Nilüfer explains that successful citizen development requires more than simply giving users access to Copilot Studio.Organizations should invest in: * Training * Mentoring * Documentation * Governance * Best practices * Secure environments The goal is enabling innovation without creating unnecessary risk. HUMAN IN THE LOOP Not every business decision should be delegated to AI.The conversation explores scenarios where human approval remains essential, particularly for: * Financial approvals * Executive decisions * Compliance processes * Sensitive business operations Human oversight remains one of the most important design principles for enterprise AI. THE FUTURE OF POWER PLATFORM Will AI replace Power Apps and Power Automate?Nilüfer believes the opposite.Rather than disappearing, these tools are becoming increasingly intelligent through AI-assisted development, natural language creation, and deeper Copilot integration.Developers will spend less time creating basic applications and more time focusing on governance, architecture, security, and user experience. ADVICE FOR FUTURE AI BUILDERS For developers just starting with Microsoft AI technologies, Nilüfer recommends beginning with freely available learning resources before investing in expensive training.She encourages developers to: * Build real projects * Follow Microsoft community experts * Watch technical YouTube channels * Experiment with Copilot Studio * Learn Azure AI fundamentals * Understand governance * Learn the architecture—not just the prompts Her message is clear: AI tools are becoming easier to use, but understanding why they work remains the key to building successful enterprise solutions. TECHNOLOGIES DISCUSSED * Microsoft Copilot Studio * Microsoft Power Platform * Power Apps * Power Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support [https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support?utm_source=rss&utm_medium=rss&utm_campaign=rss].

Reacties

0

Wees de eerste die een reactie plaatst

Meld je nu aan en word lid van de M365.FM - Modern work, security, and productivity with Microsoft 365 community!

Probeer gratis

Probeer 14 dagen gratis

€ 9,99 / maand na proefperiode. · Elk moment opzegbaar.

  • Podcasts die je alleen op Podimo hoort
  • 20 uur luisterboeken / maand
  • Gratis podcasts

Alle afleveringen

690 afleveringen

aflevering Everything Microsoft Didn't Tell You About Teams with Everything Microsoft Didn't Tell You About Teams with Josh Blalock [MVP] artwork

Everything Microsoft Didn't Tell You About Teams with Everything Microsoft Didn't Tell You About Teams with Josh Blalock [MVP]

Microsoft Teams has evolved from a simple collaboration platform into the digital workplace at the heart of modern business. But behind every successful Teams meeting lies far more than software. In this episode of the M365 FM Podcast, host Mirko Peters sits down with Microsoft MVP, Microsoft 365 Copilot expert, technology evangelist, and Comms vNext co-founder Josh Blalock to uncover the technology, strategy, and hardware innovations that most organizations never think about when deploying Microsoft Teams. From the evolution of Skype for Business to today's AI-powered collaboration experiences, Josh shares over two decades of real-world experience designing, deploying, and optimizing Microsoft collaboration solutions. Together they explore why audio quality is becoming even more important than video, how Microsoft 365 Copilot changes the value of meeting rooms, and why organizations should rethink how they invest in collaboration technology. FROM SKYPE FOR BUSINESS TO MICROSOFT TEAMS Josh reflects on his journey from managing Microsoft Exchange servers in the U.S. Air Force to becoming one of the leading experts in Microsoft Teams and Unified Communications. He explains how technologies like Office Communications Server, Lync, Skype for Business, and Microsoft Teams transformed enterprise collaboration and why cloud-first communication has completely changed the role of IT administrators. The conversation also explores what has been lost—and gained—as organizations transitioned from on-premises infrastructure to Microsoft's cloud ecosystem. WHY AUDIO MATTERS MORE THAN EVER Most companies invest heavily in cameras, displays, and meeting room aesthetics. Surprisingly, the most important technology in an AI-powered meeting room isn't the camera—it's the microphone. Josh explains why poor audio doesn't just frustrate meeting participants anymore—it directly reduces the quality of Microsoft 365 Copilot. Every transcript, meeting summary, action item, and AI-generated follow-up depends entirely on clean, accurate audio. As Copilot becomes the digital assistant for every meeting, microphone quality becomes the foundation of enterprise AI. Topics include: * Why audio is more important than video * Conference room acoustics * Digital Signal Processing (DSP) * Noise reduction and echo cancellation * AI-ready meeting rooms * Meeting transcription accuracy * Microsoft 365 Copilot meeting intelligence SHURE'S EXPANSION INTO MICROSOFT TEAMS Many people know Shure for its legendary microphones used by musicians, podcasters, broadcasters, and content creators. What many don't realize is that Shure has spent more than a decade developing enterprise conferencing technology for meeting rooms around the world. Josh explains how Shure's conferencing portfolio has evolved from premium audio hardware into complete Microsoft Teams Rooms solutions, including certified Windows and Android-based meeting room systems designed specifically for modern hybrid work. The discussion covers how hardware certification works, why Microsoft Teams certification matters, and how enterprise customers should evaluate conference room equipment before making major investments.  BUILDING THE PERFECT AI MEETING ROOM Creating a great meeting experience involves much more than simply installing a camera and microphone. Josh shares practical advice for organizations planning new collaboration spaces, including room acoustics, hardware selection, conference room design, DSP technology, furniture placement, audio processing, and working with integrators to build environments that deliver exceptional meeting experiences. As AI becomes increasingly integrated into daily collaboration, the quality of meeting room infrastructure will directly influence the quality of business intelligence generated by Microsoft 365 Copilot.  THE MICROSOFT MVP JOURNEY Josh also shares his personal story of becoming a Microsoft MVP. From writing technical blogs and publishing educational videos to building one of the Microsoft collaboration community's most respected conferences, he explains how sharing knowledge—not simply collecting certifications—is what ultimately defines successful community leadership. He also discusses the brand-new Shure Ignition Program, inspired by Microsoft's MVP Program, which supports technology evangelists and community leaders focused on Microsoft Teams Rooms and enterprise collaboration hardware.  COMMS VNEXT AND THE MICROSOFT COLLABORATION COMMUNITY The episode also takes listeners behind the scenes of Comms vNext, one of the most respected community-driven conferences dedicated to Microsoft Teams, Unified Communications, Microsoft 365, and AI-powered collaboration. Josh explains why the conference was created, how it differs from Microsoft Ignite, and why community events remain one of the best places for IT professionals to learn, network, and stay ahead of Microsoft's rapidly evolving collaboration ecosystem.  WHO SHOULD LISTEN? This episode is ideal for: * Microsoft Teams Administrators * Microsoft 365 Architects * IT Decision Makers * Collaboration Engineers * UC Specialists * Microsoft MVPs * Meeting Room Designers * Enterprise Architects * AI and Copilot Champions * Content Creators * Anyone deploying Microsoft Teams Rooms Whether you're planning your first Teams Room, investing in Microsoft 365 Copilot, evaluating enterprise collaboration hardware, or simply trying to understand where Microsoft Teams is heading next, this episode delivers practical insights that go far beyond the user interface. If you've ever wondered why some Teams meetings feel effortless while others struggle with poor audio, inaccurate transcripts, or disappointing AI experiences, this conversation explains the technology that makes the difference—and why the future of Microsoft Teams is about much more than meetings. Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support [https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support?utm_source=rss&utm_medium=rss&utm_campaign=rss].

Gisteren45 min
aflevering Beyond the Portal: The Strategic Architecture of Microsoft Graph and PowerShell artwork

Beyond the Portal: The Strategic Architecture of Microsoft Graph and PowerShell

For years, Microsoft 365 administration has been defined by portals. Administrators spend their days inside the Microsoft 365 Admin Center, Exchange Admin Center, SharePoint Admin Center, Teams Admin Center, and Intune. They click through dashboards, configure policies, manage identities, assign licenses, and respond to support tickets one task at a time. But beneath every portal lies a deeper reality. Every action performed in a Microsoft portal ultimately translates into a Microsoft Graph API call. The portal is simply a user interface layered on top of the actual control plane that powers Microsoft 365. In this episode, we explore why Microsoft Graph and PowerShell are becoming the foundation of modern Microsoft 365 administration, how organizations can move beyond manual operations toward large-scale automation, and why Graph knowledge is rapidly becoming one of the most valuable skills for Microsoft professionals. WHY THE PORTAL IS BECOMING A BOTTLENECK Portals are excellent for individual tasks. Creating a user, assigning a license, or reviewing a policy can all be completed quickly through a graphical interface. The challenge emerges when organizations need to operate at scale. Managing thousands of users, devices, groups, Teams, SharePoint sites, applications, and security controls through manual clicks creates operational overhead that compounds over time. The discussion explores how portal-driven administration often hides inefficiencies, limits visibility, and prevents organizations from leveraging the full automation capabilities available within Microsoft 365.  MICROSOFT GRAPH: THE REAL OPERATING SYSTEM OF MICROSOFT 365 Many professionals think of Microsoft Graph as simply another API. The reality is far more significant. Microsoft Graph serves as the unified access layer for Microsoft 365, connecting identities, collaboration, communication, security, compliance, and business data through a single platform. Topics discussed include: * Microsoft Graph architecture * Unified endpoint design * REST APIs * Microsoft Graph PowerShell SDK * Identity-driven access * Enterprise automation Rather than viewing Graph as an API, organizations should view it as the operational backbone of the entire Microsoft ecosystem. THE STRATEGIC IMPORTANCE OF GRAPH IN THE AI ERA Microsoft's future is increasingly built on Graph. Copilot uses Graph to retrieve organizational data. AI agents use Graph to perform actions. Copilot Studio relies on Graph-based integrations. Agentic workflows depend on Graph permissions and access controls. The episode explores why organizations investing in Graph capabilities today are simultaneously preparing for the next generation of AI-powered business systems. AUTHENTICATION, PERMISSIONS, AND ENTERPRISE SECURITY Every Graph request starts with identity. Understanding authentication and authorization is essential for building secure automation. The discussion covers: * Delegated permissions * Application permissions * Service principals * OAuth authentication * Consent models * Least privilege design A major focus is placed on avoiding excessive permissions and understanding how overprivileged applications create significant enterprise security risks. WHY PERMISSION DEBT BECOMES AN AI PROBLEM Many organizations have accumulated years of permission sprawl. SharePoint sites with broad access. Teams workspaces shared too widely. Applications with unnecessary permissions. Before AI, these issues often remained hidden. Copilot changes that. The episode explores how AI systems surface existing permission problems by making organizational data easier to discover and access through natural language interactions. Permission governance is no longer just a security initiative. It has become a prerequisite for successful AI adoption.  AUTOMATING THE COMPLETE USER LIFECYCLE One of the most practical applications of Microsoft Graph is identity lifecycle management. Instead of manually processing onboarding and offboarding requests, organizations can automate the entire lifecycle. Topics include: * User provisioning * License assignment * Group membership management * Team provisioning * Employee transfers * Offboarding automation The discussion demonstrates how Graph PowerShell can transform repetitive identity management tasks into reliable, repeatable workflows that execute consistently across thousands of users. THE IDEMPOTENT PRINCIPLE: BUILDING SAFE AUTOMATION Successful automation is not just about executing tasks. It is about executing tasks safely. The episode introduces the concept of idempotency, one of the most important principles in enterprise automation. An idempotent script can run repeatedly without causing duplicate actions, configuration drift, or unintended side effects. Key concepts include: * State validation * Safe execution patterns * Error handling * Recovery workflows * Automated remediation * Operational resilience This approach enables organizations to build automation that can operate continuously without constant human oversight. MANAGING TEAMS, SHAREPOINT, AND ONEDRIVE AT SCALE Collaboration platforms generate enormous amounts of data and governance complexity. The episode explores how Graph enables organizations to manage collaboration workloads programmatically. Topics discussed include: * Teams lifecycle management * SharePoint governance * OneDrive administration * Site provisioning * External sharing audits * Retention enforcement Rather than manually reviewing thousands of collaboration resources, organizations can use Graph to automate governance and maintain compliance continuously. GRAPH AS A SECURITY OPERATIONS PLATFORM Security teams increasingly rely on Graph for visibility and automation. The discussion explores how Graph provides access to critical security signals across Microsoft 365. Areas covered include: * Defender integration * Security APIs * Service principal monitoring * Conditional Access analysis * MFA coverage audits * Risk detection Graph enables organizations to move beyond reactive security and toward continuous monitoring and automated response capabilities. GOVERNANCE, COMPLIANCE, AND POLICY ENFORCEMENT Governance is often misunderstood as documentation. In reality, governance is about enforcement. The episode examines how organizations can leverage Graph to operationalize compliance requirements and ensure policies are consistently applied across Microsoft 365 environments. Topics include: * Sensitivity labels * Retention policies * eDiscovery readiness * Microsoft Purview integration * Audit evidence collection * Data residency controls Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support [https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support?utm_source=rss&utm_medium=rss&utm_campaign=rss].

Gisteren1 h 10 min
aflevering Think Like an Attacker: Microsoft Security Exposure Management with Uros Babic [MVP-MCT] artwork

Think Like an Attacker: Microsoft Security Exposure Management with Uros Babic [MVP-MCT]

Traditional cybersecurity focuses on vulnerabilities, alerts, and dashboards. Attackers don't. They look for opportunities, weak identities, exposed cloud resources, excessive permissions, forgotten endpoints, and misconfigurations they can chain together into a successful attack. In this episode of the M365 FM Podcast, host Mirko Peters takes a unique approach by stepping into the role of the attacker while Microsoft Security MVP and Microsoft Certified Trainer Uros Babic defends a modern Microsoft environment using Microsoft Security Exposure Management, Microsoft Defender XDR, Microsoft Sentinel, Security Copilot, and Zero Trust principles. Instead of discussing security theory, this episode follows a realistic attack scenario from reconnaissance and phishing to privilege escalation, lateral movement, ransomware, and data exfiltration. Along the way, Uros explains how organizations can stop attackers before they reach critical assets by focusing on exposure rather than simply fixing vulnerabilities. The discussion demonstrates why modern security operations are shifting from reactive incident response to proactive risk reduction powered by Microsoft's latest security technologies. THINKING LIKE AN ATTACKER The episode begins with one fundamental mindset shift: attackers don't see security dashboards or compliance reports—they see attack paths. Uros explains why organizations should stop asking "How many vulnerabilities do we have?" and instead ask "Which attack path would an attacker exploit first?" Topics include: * Social engineering * Phishing attacks * Credential theft * Privilege escalation * Lateral movement * Ransomware * Data exfiltration * Insider threats * Supply chain attacks * Cloud misconfigurations Understanding how attackers think is becoming one of the most valuable skills for every modern security team. MICROSOFT SECURITY EXPOSURE MANAGEMENT One of the central topics is Microsoft's Security Exposure Management platform. Unlike traditional vulnerability management, Exposure Management connects identities, endpoints, cloud resources, permissions, applications, and attack paths into a single security graph that helps organizations prioritize what actually matters. Rather than fixing thousands of isolated vulnerabilities, security teams can identify the fastest route an attacker could take to reach Tier-0 assets and eliminate those paths before they are exploited. The discussion covers: * Exposure Graph * Attack Path Analysis * Attack Surface Management * Risk Prioritization * Critical Asset Protection * Continuous Threat Exposure Management (CTEM) * Microsoft Defender Portal * Multi-cloud visibility AI, SECURITY COPILOT & AGENTIC SECURITY Artificial Intelligence is transforming cybersecurity for both defenders and attackers. Uros explains how Microsoft Security Copilot helps security analysts investigate incidents faster, summarize complex alerts, analyze malicious scripts, recommend remediation steps, and automate repetitive SOC workflows. The conversation also explores how AI agents introduce entirely new security challenges. Organizations must now secure AI agents just like human identities by applying Conditional Access, Microsoft Entra ID, Identity Protection, Microsoft Purview, and governance policies. As enterprises deploy more AI-powered assistants, securing Agentic AI becomes a critical part of every Zero Trust strategy.  ZERO TRUST IN THE AGE OF AI Zero Trust remains one of Microsoft's core security principles—but AI changes how organizations must apply it. The discussion explores how Zero Trust combines with Exposure Management to answer an even more important question: "Even if nothing is trusted, what can an attacker still exploit?" Topics include: * Identity Protection * Conditional Access * Passwordless Authentication * Managed Devices * Microsoft Entra ID * Defender for Cloud Apps * Microsoft Purview * AI Governance * Security Policies The result is a proactive security model that continuously reduces exposure instead of simply responding to incidents. BUILDING A MODERN SECURITY OPERATIONS CENTER Many organizations still measure security success by counting alerts or tracking ticket volumes. Uros explains why these metrics often create a false sense of security. Modern SOC teams should instead focus on: * Exposure reduction * Attack path elimination * Tier-0 asset protection * Critical exposure remediation * MITRE ATT&CK coverage * Identity risk reduction * Security posture improvements By measuring business risk instead of operational activity, security teams become far more effective against today's sophisticated attackers. CYBERSECURITY CAREERS AND COMMUNITY Beyond technology, Uros shares valuable career advice for professionals interested in cybersecurity. He recommends building strong networking and infrastructure fundamentals before specializing in cloud security and emphasizes that practical hands-on experience is often more valuable than collecting certifications alone. The conversation also covers learning platforms, Microsoft certifications, community engagement, and the importance of continuously adapting as cybersecurity evolves alongside AI.  WHO SHOULD LISTEN?  This episode is ideal for: * Security Architects * SOC Analysts * Microsoft 365 Administrators * Azure Engineers * Cloud Architects * IT Decision Makers * Microsoft MVPs * Security Consultants * CISOs * DevSecOps Engineers * Anyone responsible for securing Microsoft environments Whether you're deploying Microsoft Defender XDR, Microsoft Sentinel, Microsoft Security Copilot, Microsoft Entra, Microsoft Purview, or simply looking to better understand how modern attackers operate, this episode provides practical insights into building a proactive security strategy. If you want to stop reacting to security incidents and start thinking like an attacker, this conversation offers a comprehensive look at why Microsoft Security Exposure Management is becoming one of the most important innovations in enterprise cybersecurity. Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support [https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support?utm_source=rss&utm_medium=rss&utm_campaign=rss].

2 jul 20261 h 9 min
aflevering Stop Building Bots, Start Building Runtimes: A Field Guide to Microsoft Agents artwork

Stop Building Bots, Start Building Runtimes: A Field Guide to Microsoft Agents

Everyone is calling Build 2026 the AI conference. Most of the attention went toward new copilots, voice experiences, and increasingly capable models. But beneath the headlines, Microsoft quietly introduced something far more significant. The real story is not about another AI feature. It is about the emergence of a completely new infrastructure layer for enterprise computing. For years, organizations approached AI as a chatbot problem. Build a conversational interface, connect it to some data, add a few prompts, and call it an AI strategy. That approach worked for experimentation, but it was never designed for scale. Chatbots forget context, struggle with governance, and become increasingly difficult to manage as more departments begin building their own solutions. What Microsoft is building now is fundamentally different. We are moving from assistants that answer questions to agents that operate as active participants inside the enterprise. THE FOUR-LAYER MODEL THAT CHANGES EVERYTHING One of the most important concepts emerging from Microsoft's latest announcements is the idea that agents should no longer be viewed as products. They should be viewed as layers within a larger system. Most organizations currently evaluate AI by comparing products. They ask whether they should use Copilot, Copilot Studio, Azure AI Foundry, GitHub Copilot, or Security Copilot. That approach creates confusion because these technologies solve very different problems. The better way to think about agents is through architecture. The modern agent stack consists of four distinct layers: * Experience Layer * Agent Layer * Runtime Layer * Governance Layer Each layer serves a unique purpose. Each layer has different stakeholders. And each layer introduces different operational requirements. Organizations that understand this distinction can scale successfully. Organizations that ignore it often end up with fragmented deployments and duplicated effort. WHY IDENTITY IS THE REAL STORY The most important announcement from Build 2026 was not a new agent. It was identity. Historically, automation systems operated through shared service accounts. Scripts, bots, and integrations all ran under generic credentials that nobody really owned. This created security blind spots and made auditing nearly impossible. When something happened, it was difficult to determine which system actually performed the action. Microsoft's new model changes that entirely. Every agent now receives its own identity inside Microsoft Entra. Every agent becomes a first-class principal within the organization. It has its own permissions, its own audit trail, and its own lifecycle. This seemingly small architectural change creates enormous downstream benefits: * Least-privilege access * Full auditability * Conditional Access enforcement * Individual credential management * Instant revocation capabilities For the first time, agents are being treated like actual actors inside the enterprise rather than invisible background processes. This shift enables governance at a scale that simply wasn't possible before. THE RISE OF AGENT INFRASTRUCTURE Most organizations are still focused on building individual agents. The problem is that individual agents are only part of the story. Real business value emerges when agents work together. A retrieval agent gathers information. An analysis agent interprets it. A communication agent creates output. A coordinating agent manages the workflow. Suddenly, what looked like a chatbot becomes an operational system. This is where Azure AI Foundry Agent Service enters the picture. Foundry provides the runtime environment where agents actually execute. It handles: * Memory management * Session persistence * Multi-agent orchestration * Tool discovery * State management Instead of developers spending months building infrastructure, they can focus on defining agent behavior while Microsoft manages scaling, networking, and execution behind the scenes. This dramatically reduces complexity and accelerates deployment timelines. THE SHADOW AGENT PROBLEM One of the most fascinating challenges discussed in this episode is something many organizations have not yet recognized. The Shadow Agent problem. Building agents is becoming incredibly easy. Governance is not. As a result, business units increasingly create their own agents without involving IT. Sales teams build lead qualification agents. Operations teams create workflow automations. Individual departments experiment with Copilot Studio and Power Platform. Before long, dozens or even hundreds of agents are operating across the organization without centralized visibility. This creates significant risks: * Duplicate functionality * Excessive permissions * Compliance concerns * Data leakage risks * Lack of ownership Agent 365 is Microsoft's answer to this challenge. It provides centralized discovery, governance, identity management, auditing, and policy enforcement across the entire agent ecosystem. The goal is not to stop innovation. The goal is to make innovation manageable. FROM ASSISTANCE TO AUTOMATION The biggest change is not technical. It is organizational. For years, AI systems were designed to assist humans. The human remained the primary actor while AI provided recommendations and suggestions. The new generation of agents flips that relationship. The agent executes. The human supervises. Sales qualification becomes automated. Security triage becomes automated. Financial reconciliation becomes automated. Humans focus on judgment, strategy, relationships, and decision-making while agents handle repetitive operational work. This fundamentally changes how organizations think about productivity. Instead of helping employees complete tasks faster, agents begin completing entire categories of tasks on their own. Humans shift toward oversight, governance, and exception handling. THE FUTURE ISN'T MORE CHATBOTS Build 2026 may ultimately be remembered as the moment agents stopped being experimental technology and started becoming enterprise infrastructure. The organizations that succeed over the next decade will not be the ones with the most chatbots. They will be the ones that understand identity, governance, orchestration, runtime architecture, and multi-agent systems. They will build platforms rather than isolated tools. The future of enterprise AI is not conversational. The future of enterprise AI is operational. And Microsoft has just laid the foundation for that future. Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support [https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support?utm_source=rss&utm_medium=rss&utm_campaign=rss].

2 jul 20261 h 16 min
aflevering EXTENSIBILITY FIRST: Building .NET Systems That Survive Change with Miguel Castro [MVP] artwork

EXTENSIBILITY FIRST: Building .NET Systems That Survive Change with Miguel Castro [MVP]

Software rarely fails because developers cannot write code. It fails because applications are designed for today's requirements instead of tomorrow's changes. In this episode of the m365.fm Podcast, Mirko Peters sits down with Microsoft MVP Miguel Castro—software architect, consultant, conference speaker, and one of the most respected voices in the .NET ecosystem—to explore why extensibility should be the foundation of every enterprise application. With decades of experience designing cloud SDKs, enterprise communication platforms, AI-powered transcription systems, automation solutions, and scalable .NET applications, Miguel shares the architectural mindset that has helped organizations build software capable of evolving for years instead of becoming technical debt after only a few releases. Rather than focusing on trendy frameworks or the latest development buzzwords, this conversation dives into timeless software engineering principles. Miguel explains why clean code starts long before writing the first line of C#, how modular thinking simplifies maintenance, and why extensibility isn't overengineering—it's preparing your software for the reality that requirements will always change. Whether you're a .NET developer, software architect, engineering manager, technical lead, or CTO, this episode offers practical insights that can immediately improve the way you design modern enterprise systems. WHAT YOU'LL LEARN  During this episode you'll discover: * Why extensibility is the cornerstone of maintainable enterprise software * The difference between writing clean code and designing great architecture * How modular systems dramatically reduce future development costs * Why strategy patterns, abstractions, and dependency injection work so well together * How AI is changing software development without replacing software architects WHY EXTENSIBILITY MATTERS MORE THAN EVER Every successful software product evolves. New business requirements appear. Customers request additional features. Security standards change. AI capabilities emerge. Integrations become necessary. Miguel explains that applications designed around extensibility can adapt to these changes by replacing or extending individual components instead of rewriting entire systems. Through practical examples—including AI-powered transcription platforms, enterprise automation solutions, and communication SDKs—he demonstrates how designing for change dramatically reduces maintenance costs while increasing long-term business value. One of the biggest takeaways is that architecture should make future changes easier, not harder. Great architecture often becomes invisible because it simply allows software to evolve naturally.  CLEAN CODE STARTS WITH GREAT ARCHITECTURE Many developers focus heavily on writing clean, readable code. Miguel argues that clean code is actually the result of good architectural decisions made before implementation begins. The discussion explores layering, modularity, abstraction, component boundaries, dependency injection, interfaces, design patterns, and the importance of separating responsibilities early in a project. You'll also hear why architecture and implementation should never become isolated disciplines, and why architects and developers must continuously collaborate throughout the software lifecycle.  AI, AUTOMATION & THE FUTURE OF .NET DEVELOPMENT Artificial Intelligence is transforming how developers build software, but Miguel believes its greatest value lies in accelerating implementation—not replacing architectural thinking. The conversation covers: * AI-assisted coding * Azure AI services * Enterprise automation * AI-powered transcription systems * Knowledge retrieval * ChatGPT integrations * Developer productivity * Responsible AI-assisted development Miguel explains where AI delivers enormous productivity gains and where human experience remains irreplaceable, especially when designing complex enterprise systems. DESIGN PATTERNS THAT ACTUALLY MATTER Instead of discussing patterns theoretically, Miguel shares the real-world architectural approaches he relies on throughout enterprise consulting projects. Topics include strategy patterns, abstraction, plugin architectures, event-driven extensibility, HTTP pipeline concepts inspired by ASP.NET, modular application design, dependency injection, and techniques for building software that remains adaptable long after its first deployment. RAPID FIRE QUESTIONS The episode concludes with an entertaining rapid-fire session covering developer preferences and opinions on topics including: * REST vs GraphQL * Clean Architecture vs Vertical Slice Architecture * Azure Functions vs Containers * Essential C# language features * Extension methods * Async/Await * AI coding assistants * Favorite developer beverages * Modern .NET development practices ABOUT MIGUEL CASTRO Miguel Castro is a Microsoft MVP, Senior .NET Software Architect, consultant, international conference speaker, and longtime expert in enterprise application architecture. Throughout his career he has designed communication platforms, cloud SDKs, enterprise automation systems, AI-powered applications, and scalable software solutions that continue evolving long after deployment. His passion for extensible software architecture has helped countless organizations build applications that survive changing business requirements instead of becoming expensive technical debt.  LISTEN IF YOU WANT TO LEARN ABOUT  .NET, C#, Software Architecture, Enterprise Software Development, Extensibility, Clean Architecture, Modular Design, Strategy Pattern, Dependency Injection, Design Patterns, ASP.NET, Azure AI, Artificial Intelligence, Enterprise Automation, Technical Leadership, Developer Productivity, Scalable Systems, Plugin Architecture, Microservices, Cloud Development, Software Engineering Best Practices. Become a supporter of this podcast: https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support [https://www.spreaker.com/podcast/m365-fm-modern-work-security-and-productivity-with-microsoft-365--6704921/support?utm_source=rss&utm_medium=rss&utm_campaign=rss].

1 jul 20261 h 4 min