Holger Imbery
Microsoft MVP Business Applications - Copilot Studio & MCT & PowerPlatform | Azure | Dynamics - principal architect @NTTData Inc.
Microsoft MVP Business Applications - Copilot Studio & MCT & PowerPlatform | Azure | Dynamics - principal architect @NTTData Inc.
Berlin, Germany
Actions
Holger is a principal architect with over 20 years of experience in designing workplace solutions, specializing in Microsoft Power Platform and Microsoft Azure.
He shares his expertise and knowledge about the Power Platform, particularly on Copilot Studio, with the community through blogging and speaking at events.
Holger ist ein principal architect mit über 20 Jahren Erfahrung in der Gestaltung von Arbeitsplatzlösungen, spezialisiert auf Microsoft Power Platform und Microsoft Azure.
Er teilt sein Fachwissen und seine Kenntnisse über die Power Platform, insbesondere über Copilot Studio, mit der Community durch Bloggen und Vorträge auf Veranstaltungen.
Links
Area of Expertise
Topics
Rethinking Test Automation: Streamlining Agent Development with the Copilot Studio Kit (lowcode) en de
Discover how the Copilot Studio Kit transforms test automation for custom agents built in Microsoft Copilot Studio. In this 30-minute session, you'll get a hands-on look at how this innovative toolkit simplifies and accelerates the development and testing process.
What you’ll learn:
- Introduction to the Copilot Studio Kit: A quick overview of its purpose and core capabilities.
- Key Features: Deep dive into the unique functionalities that make the kit stand out.
- Workflow Optimization: Live demonstrations showing how the kit enhances efficiency in development and testing.
- Real-World Use Cases: Practical examples that highlight the kit’s impact across different scenarios.
By the end of the session, you’ll understand how to leverage the Copilot Studio Kit to improve reliability, reduce development time, and scale your (lowcode) custom agent solutions with confidence.
Target Audience: Developers, QA engineers, and technical leads working with Copilot Studio or exploring automated agent development.
Level: Intermediate
Testautomatisierung neu gedacht: Entwicklung von Agents mit dem Copilot Studio Kit (lowCode) en de
Erleben Sie, wie das Copilot Studio Kit die Testautomatisierung für benutzerdefinierte Agenten revolutioniert. In dieser 30-minütigen Session erhalten Teilnehmende einen praxisnahen Einblick in die innovativen Funktionen und Möglichkeiten des Kits – speziell entwickelt, um die Entwicklung und das Testen von Custom Agents in Copilot Studio effizienter und zuverlässiger zu gestalten.
Was Sie erwartet:
- Einführung in das Copilot Studio Kit: Überblick über die wichtigsten Funktionen und den Mehrwert für Entwickler:innen.
- Innovative Features im Detail: Vorstellung der einzigartigen Funktionen, die das Kit von anderen Tools abheben.
- Optimierung von Entwicklungsprozessen: Live-Demonstrationen, wie das Kit Workflows beschleunigt und vereinfacht.
- Praxisbeispiele: Konkrete Anwendungsszenarien aus dem Alltag, die die Effektivität des Kits belegen.
Lernziele:
Nach der Session verstehen Sie, wie das Copilot Studio Kit Ihre LowCode Testautomatisierung transformieren kann – von der Entwicklung bis zur produktiven Nutzung Ihrer Custom Agents. Sie nehmen direkt umsetzbare Impulse mit, um Ihre Projekte schneller, skalierbarer und robuster zu gestalten.
Zielgruppe: Entwickler:innen, QA-Spezialist:innen und technische Entscheider:innen, die mit Copilot Studio arbeiten oder den Einstieg in die automatisierte Agentenentwicklung planen.
Level: Mittelstufe
Building Autonomous Agents with Copilot Studio: A Practical Introduction en de
In this 30-minute session, attendees will explore how to build and integrate autonomous agents using Microsoft Copilot Studio. We’ll begin with a concise overview of Copilot Studio’s core capabilities, followed by a clear explanation of what autonomous agents are—expert systems designed to act independently on behalf of a process or organization.
The session will then dive into the technical integration of autonomous agents within Copilot Studio, showcasing real-world examples with a focus on customer service scenarios.
You’ll learn how these agents can be configured to handle voice-based interactions, automate routine tasks, and deliver consistent, scalable support.
By the end of the session, participants will understand:
- The foundational concepts of autonomous agents
- How to technically implement them in Copilot Studio
- Key benefits for customer service, including 24/7 availability, cost-efficiency, and scalability
We’ll wrap up with an interactive Q&A to address your specific use cases and challenges.
Target Audience: Developers, solution architects, and tech leads interested in AI-driven automation, customer service innovation, and Microsoft ecosystem tools.
Level: Intermediate
Autonome Agenten mit Copilot Studio entwickeln – Ein praxisnaher Einstieg en de
In dieser 30-minütigen Session erhalten die Teilnehmenden einen praxisorientierten Einstieg in die Entwicklung und Integration autonomer Agenten mit Microsoft Copilot Studio.
Nach einer kompakten Einführung in die zentralen Funktionen von Copilot Studio wird erläutert, was autonome Agenten sind – nämlich Expertensysteme, die selbstständig im Auftrag eines Unternehmens oder Prozesses agieren.
Im Anschluss folgt ein technischer Deep Dive zur Integration solcher Agenten in Copilot Studio, ergänzt durch konkrete Anwendungsbeispiele aus dem Bereich Kundenservice. Dabei wird gezeigt, wie autonome Agenten für sprachbasierte Interaktionen konfiguriert werden können, um Routineaufgaben zu automatisieren und konsistente, skalierbare Unterstützung zu bieten.
Am Ende der Session wissen die Teilnehmenden:
- Was autonome Agenten sind und wie sie funktionieren
- Wie sie technisch in Copilot Studio umgesetzt werden
- Welche Vorteile sie insbesondere im Kundenservice bieten
– darunter 24/7-Verfügbarkeit, Effizienzsteigerung und Kostensenkung
Die Session schließt mit einer offenen Q&A-Runde, in der individuelle Fragen und Anwendungsfälle besprochen werden können.
Zielgruppe: Entwickler:innen, Solution Architects und technische Entscheider:innen mit Interesse an KI-gestützter Automatisierung und Microsoft-Technologien
Level: Intermediate
Orchestrating Multi‑Agent Systems in Microsoft Copilot Studio en de
Design patterns for nested (child) agents, connected agents, A2A collaboration, and MCP‑enabled autonomous agents
In this 60‑minute workshop, you'll learn how to design, compose, and operate multi‑agent solutions in Microsoft Copilot Studio. We'll walk through reference architectures, live demos, and guardrails that let you safely scale from a single copilot to a resilient multi‑agent topology — covering nested (child) agents, connected agents, Agent‑to‑Agent (A2A) messaging, and Model Context Protocol (MCP) integrations.
What you’ll learn:
Multi‑Agent Architecture Fundamentals
How to model roles, capabilities, boundaries, and context across agents. Patterns for planner/executor, broker/worker, and supervisor/child topologies.
Nested (Child) Agents
When and how a parent agent spawns specialized child agents; lifecycle and termination; context scoping, memory sharing, and capability delegation. Practical guardrails for escalation, retries, and fallbacks.
Connected Agents
Connecting agents to data and actions through plugins/connectors (e.g., business systems, knowledge bases, workflows). Designing stable contracts (schema, intents, error shapes) and capability registries to keep connections manageable at scale.
Agent‑to‑Agent (A2A) Collaboration
Message patterns (request/response, async handoff, pub/sub), routing and arbitration, negotiation and role handover, and how to instrument traces for observability and root‑cause analysis.
MCP
How to leverage Model Context Protocol (MCP) to expose tools/resources to autonomous agents: capability discovery, permissioning, invocation, and result normalization. Safety strategies (bounded autonomy, human‑in‑the‑loop checkpoints, policy enforcement).
Governance & Safety
Data access boundaries, least‑privilege design, auditability, incident response playbooks, and rollout strategies that minimize risk while enabling innovation.
By the end of the session, you will be able to:
Design robust multi‑agent solutions with clear roles, contracts, and governance.
Implement nested and connected agent patterns that scale without losing control.
Enable A2A collaboration with traceable handoffs and measurable reliability.
Integrate MCP tools to expand agents' capabilities.
Apply testing and observability practices to reduce intervention and improve outcomes.
Target Audience:
Solution architects, developers, and technical leads building agents in Copilot Studio or scaling to multi‑agent systems and autonomous behaviors.
Level: Intermediate (with advanced design patterns).
Orchestrating Multi‑Agent Systems in Microsoft Copilot Studio en de
Design Patterns für Nested (Child) Agents, Connected Agents, A2A Collaboration und MCP
In diesem 60‑minütigen Workshop lernen Sie, wie Sie Multi‑Agent‑Lösungen in Microsoft Copilot Studio entwerfen, zusammensetzen und betreiben. Wir zeigen Referenzarchitekturen, Live-Demos und Guardrails, die es Ihnen ermöglichen, sicher von einem einzelnen Copilot zu einer robusten Multi‑Agent‑Topologie zu skalieren – inklusive Nested (Child) Agents, Connected Agents, Agent‑to‑Agent (A2A) Messaging und Model Context Protocol (MCP)‑Integration.
Was Sie lernen werden:
Grundlagen der Multi‑Agent‑Architektur
Wie Sie Rollen, Fähigkeiten, Grenzen und Kontexte über mehrere Agents hinweg modellieren. Patterns für Planner/Executor‑, Broker/Worker‑ und Supervisor/Child‑Topologien.
Nested (Child) Agents
Wann und wie ein Parent Agent spezialisierte Child Agents erzeugt; Lifecycle und Terminierung; Context Scoping, Memory Sharing und Capability Delegation. Praktische Guardrails für Eskalationen, Wiederholungen und Fallbacks.
Connected Agents
Agents über Plugins/Connectors (z. B. Business-Systeme, Wissensdatenbanken, Workflows) mit Daten und Aktionen verbinden. Design stabiler Contracts (Schema, Intents, Error Shapes) und Capability Registries, um Verbindungen skalierbar und beherrschbar zu halten.
Agent‑to‑Agent (A2A) Collaboration
Message Patterns (Request/Response, Async Handoff, Pub/Sub), Routing und Arbitration, Verhandlung und Rollenübergabe sowie die Instrumentierung von Traces für Observability und Root‑Cause‑Analyse.
MCP
Wie Sie das Model Context Protocol (MCP) nutzen, um Tools und Ressourcen für autonome Agents bereitzustellen: Capability Discovery, Permissioning, Invocation und Result Normalization. Sicherheitsstrategien (Bounded Autonomy, Human‑in‑the‑Loop Checkpoints, Policy Enforcement).
Governance & Safety
Datenzugriffsgrenzen, Least‑Privilege‑Design, Auditierbarkeit, Incident‑Response‑Playbooks und Rollout‑Strategien, die Risiken minimieren und Innovation ermöglichen.
Am Ende der Session können Sie:
Robuste Multi‑Agent‑Lösungen mit klaren Rollen, Contracts und Governance entwerfen.
Nested- und Connected-Agent‑Patterns implementieren, die skalieren, ohne dabei die Kontrolle zu verlieren.
A2A‑Collaboration mit nachvollziehbaren Handoffs und messbarer Zuverlässigkeit ermöglichen.
MCP‑Tools integrieren.
Testing- und Observability‑Praktiken anwenden, um Eingriffe zu reduzieren und Ergebnisse zu verbessern.
Zielgruppe:
Solution Architects, Developer und Technical Leads, die Agents in Copilot Studio entwickeln.
Level:
Intermediate (mit fortgeschrittenen Design Patterns).
Revolutionizing Customer Service with Autonomous Agents and Dynamics 365 Customer Service en de
Join us for an insightful talk on how autonomous agents can transform how organizations handle incoming email inquiries when integrated with Dynamics 365 Customer Service and Dynamics 365 Contact Center.
Discover how leveraging advanced AI technologies can introduce self-service options, streamline ticket creation, and ensure seamless human escalation when necessary. This session will cover:
Self-Service Solutions: Learn how autonomous agents can empower customers to resolve their issues independently, reducing the load on human agents and improving response times.
Automated Ticket Creation: Explore how AI can automatically generate and categorize tickets from incoming emails, ensuring no customer query goes unnoticed.
Efficient Human Escalation: Understand the mechanisms for escalating complex issues to human agents, ensuring that customers receive the personalized attention they need when it matters most.
By the end of this talk, you will understand how combining autonomous agents with Dynamics 365 Customer Service can enhance customer satisfaction, optimize operational efficiency, and drive business success.
Verbesserung des Kundenservice mit autonomen Agenten und Dynamics 365 Customer Service. en de
In diesem Vortrag zeigen wir ihnen auf wie autonome Agenten die Bearbeitung eingehender E-Mail-Anfragen revolutionieren können, wenn sie in Dynamics 365 Customer Service und Dynamics 365 Contact Center integriert sind.
Erfahren Sie, wie fortschrittliche KI-Technologien Selfservice- Optionen einführen, die Ticket-Erstellung optimieren und bei Bedarf eine nahtlose menschliche Eskalation sicherstellen können.
In diesem Vortrag behandeln wir folgende Themen:
Selfservice: Erfahren Sie, wie autonome Agenten Ihre Kunden befähigen können, ihre Probleme eigenständig zu lösen. Dadurch wird die Belastung Ihrer menschlichen Agenten verringert und die Reaktionszeiten werden verbessert.
Automatisierte Ticketerstellung: Entdecken Sie, wie KI automatisch Tickets aus eingehenden E-Mails generieren und kategorisieren kann, sodass keine Kundenanfrage unbeachtet bleibt.
Effiziente menschliche Eskalation: Verstehen Sie die Mechanismen zur Eskalation komplexer Probleme an menschliche Agenten, um sicherzustellen, dass Ihre Kunden die persönliche Aufmerksamkeit erhalten, die sie benötigen, wenn es darauf ankommt.
Am Ende dieses Vortrags werden Sie verstehen, wie die Kombination autonomer Agenten mit Dynamics 365 Customer Service die Kundenzufriedenheit verbessern, die betriebliche Effizienz optimieren und den Geschäftserfolg vorantreiben kann.
Multi Agent Orchestration in Copilot Studio en
In this 60‑minute presentation, you'll learn how to design, compose, and operate multi‑agent solutions in Microsoft Copilot Studio's new agent experience. We'll walk through reference architectures, live demos, and governance patterns that help you scale from a single agent to a resilient multi‑agent ecosystem using Skills, Connected Agents, Agent‑to‑Agent (A2A) collaboration, and Model Context Protocol (MCP) integrations.
What You'll Learn
* Multi‑Agent Architecture Fundamentals
Learn how to model roles, capabilities, boundaries, and context across agents. Explore common orchestration patterns such as planner/executor, broker/worker, and supervisor/specialist designs. Understand when to keep capabilities within a single agent and when to distribute them across reusable skills or autonomous agents.
* Skills: Modular Capabilities in the New Copilot Experience
In the new Copilot Studio experience, Skills provide a reusable and composable way to extend an agent's capabilities. Skills are self-contained, markdown-based capabilities that the orchestration engine can dynamically invoke when a user's request matches their purpose.
You'll learn:
How to design and structure reusable skills
Skill descriptions, instructions, and orchestration triggers
When to use a skill instead of a connected agent
Packaging and sharing skills across multiple agents
Creating specialist capabilities without increasing orchestration complexity
Designing skills that leverage tools, knowledge, and workflows effectively
We'll demonstrate how complex agent behavior can be decomposed into reusable capabilities while maintaining clarity, reusability, and governance.
Rethinking Test Automation: ship your agents with confidence en
Description
Session Overview
Discover how Agent Evaluation and related tools are transforming test automation for custom agents built with Microsoft Copilot Studio.
In this session, you’ll get a hands-on introduction to how agent evaluation streamlines development workflows, accelerates testing cycles, and improves overall agent quality.
What You’ll Learn
Agent Evaluation Explained
A concise introduction to the purpose, concepts, and core capabilities of agent evaluation.
Key Capabilities
A deep dive into the features that distinguish agent evaluation as a foundation for reliable agent testing.
Optimizing Development and Testing Workflows
Live demonstrations showing how agent evaluation improves efficiency across development, validation, and testing stages.
Real-World Use Cases
Practical examples illustrating how agent evaluation delivers value in different scenarios and enterprise contexts.
Takeaways
By the end of the session, you’ll understand how to leverage agent evaluation to:
Improve the reliability and consistency of custom agents
Reduce development and testing time
Confidently scale low-code agent solutions
Audience & Level
Target Audience: Developers, QA engineers, and technical leads working with Copilot Studio or evaluating automated agent development
Level: Intermediate
When the Auto Attendant Learns to Talk: From Teams Phone to AI-Powered Voice Agents en
Building Voice Agents with Teams Phone and Copilot Studio
Microsoft is bringing conversational AI directly into Teams Phone — and in this session, we will build it live, step by step, rather than just talk about the architecture.
You'll see how a Teams Phone Agent can greet callers, answer questions based on enterprise knowledge sources, handle appointment scheduling, and intelligently route calls through conversational routing based on intent and context — all out of the box and without writing custom code.
When interactions require organization-specific business processes — such as prescription refills, outage reporting, account inquiries, claims processing, service requests, or invoice status checks — a custom Voice Agent built in Microsoft Copilot Studio takes over seamlessly through either hand-off or direct dial integration.
Beyond the technology, we'll focus on the business value of AI-powered voice experiences:
* Reduce call center workload through automation of routine inquiries
* Improve customer and employee experiences with 24/7 self-service
* Accelerate response times and first-contact resolution
* Scale service operations without proportional increases in staffing
* Create a consistent conversational experience across channels
* Extend existing Teams Phone investments with AI-driven capabilities
This is a highly practical session. We will walk through the actual implementation process in Teams Admin Center and Microsoft Copilot Studio, covering resource accounts, classic orchestration, dynamic routing using tags, and the integration patterns required for production deployments. We will also highlight the pitfalls, configuration challenges, and lessons learned that are often overlooked in demos but become critical in real-world projects.
Using realistic scenarios from healthcare, banking, pharmacy, and utilities, you'll gain a clear understanding of where conversational AI delivers measurable business outcomes today—and where human expertise should remain part of the process.
What attendees will learn
A proven setup approach for both integration patterns: hand-off and direct dial
How to connect Teams Phone Agents with custom Copilot Studio voice agents
Best practices for conversational routing and intelligent call transfer
Common implementation challenges and how to avoid them
Where AI-powered voice automation delivers the highest business value
How to design scalable customer service and employee support experiences using the Microsoft ecosystem
The Invisible Bill - Agent FinOps en
AI cost management is entering a new era.
Traditional cloud FinOps taught us how to govern compute, storage, and infrastructure. Generative AI introduced token-based cost models. But autonomous agents fundamentally change the equation. A single request can trigger planning loops, model calls, memory retrieval, MCP servers, connected agents, workflows, evaluations, and tool execution across multiple systems before producing a result.
With the arrival of the GitHub Copilot harness in Microsoft Copilot Studio, organizations can now build sophisticated agentic solutions using advanced reasoning models, connected agents, memory, skills, and autonomous workflows. The same technology that powers GitHub Copilot's coding agent and Copilot Cowork is now available for enterprise business processes, bringing unprecedented capabilities but also new challenges in cost governance and operational visibility.
In this session, we introduce the concept of Agent FinOps and provide a practical framework for measuring, allocating, governing, and optimizing costs across agentic systems. We will explore how Copilot Credits are consumed, why traditional token-focused reporting is no longer sufficient, how to establish ownership and chargeback models, and which controls are available in Copilot Studio and the broader Microsoft Copilot ecosystem.
Using real-world enterprise scenarios, we will examine multi-agent architectures, connected agents, MCP integrations, evaluation pipelines, and autonomous workflows, highlighting where cost accumulates and how architects can prevent runaway spend without slowing innovation.
Whether you are deploying your first enterprise agent or scaling hundreds of autonomous copilots, this session will equip you with the governance patterns needed to balance innovation, accountability, and business value.
Key Takeaways
After attending this session, participants will be able to:
* Understand why Agent FinOps differs from traditional cloud FinOps and GenAI cost management.
* Identify the major cost drivers within Copilot Studio, Copilot Cowork, and agentic architectures.
* Understand how Copilot Credits are consumed across reasoning, grounding, tool usage, workflows, memory, and evaluations.
* Design chargeback and showback models for enterprise AI initiatives.
* Apply governance controls for autonomous agents, multi-agent systems, MCP servers, and connected agents.
* Establish KPIs that connect AI spending to measurable business outcomes.
* Build an Agent FinOps operating model that scales from pilot projects to enterprise-wide deployments.
Nordic Summit 2026 Sessionize Event Upcoming
European Power Platform Conference (EPPC26) Sessionize Event
ColorCloud Hamburg 2026 Sessionize Event
Global Power Platform Bootcamp 2026 | Zürich Edition - #GPPBZH Sessionize Event
Dynamics Summit 09. & 10. Dezember 2025 Sessionize Event
Microsoft AI Tour
Unleashing Autonomous Agents with Copilot Studio: From Prompts to Purpose
Session code: LTG188-DE
We'll explore how Copilot Studio empowers creators to build intelligent, goal-driven autonomous agents that go beyond simple task automation. Covering what autonomous agents are and how they differ from traditional bots, key components in Copilot Studio for building agents, and a real-world use case. Whether you're a seasoned maker or simply curious about the future of AI-driven workflows, this session will inspire ideas and demonstrate how to start working with autonomous agents in Copilot Studio.
Power Summit 15. + 16.07.2025 Sessionize Event
Holger Imbery
Microsoft MVP Business Applications - Copilot Studio & MCT & PowerPlatform | Azure | Dynamics - principal architect @NTTData Inc.
Berlin, Germany
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top