25 Years of SharePoint: From Document Libraries to Intelligent Knowledge
SharePoint has just turned 25 — and it has quietly evolved from a document repository into an AI-grounded knowledge platform.
In this session, we’ll take a fast, honest journey through SharePoint’s evolution:
• What SharePoint was really built for
• Why document libraries were never “just storage”
• How AI, Syntex, Search, and Copilot changed the game
• What it means to design SharePoint for humans and AI
Through real-world examples and light demos, we’ll explore how modern SharePoint enables intelligent content, trustworthy Copilot responses, and enterprise-ready governance
Agentic AI in the Enterprise: Designing Beyond Chatbots
Enterprises are rapidly moving beyond traditional chatbots toward AI systems that can plan, reason, and take action.
In this session, we explore what Agentic AI really means in practical terms and how it differs from chatbots and copilots. We will walk through the agentic lifecycle (goal → plan → act → observe → iterate), common enterprise architecture patterns, and how platforms such as Copilot Studio, Power Automate, Dataverse, and Azure OpenAI work together to enable these solutions.
Users will learn how to design single-agent and multi-agent systems, where to introduce human-in-the-loop controls, and how to apply responsible AI principles such as least-privilege access, auditing, and monitoring.
The session focuses on design thinking and real-world patterns rather than tool demos, helping architects and developers build AI agents that can safely move from prototype to production.
Designing Responsible AI Agents with MCP: From Copilot Studio to Azure Agents
Modern AI agents do not operate in isolation. They are part of a connected ecosystem that brings together user experience, enterprise data, business workflows, and governance controls.
In this ecosystem, Copilot Studio enables business users to build conversational and task-based agents integrated with Microsoft 365, Teams, and enterprise knowledge. Azure Agents provide advanced orchestration, tool execution, and integration with enterprise systems such as APIs, databases, and custom services.
The Model Context Protocol (MCP) introduces a structured layer that standardizes how agents access tools, manage context, and execute actions in a controlled and predictable manner. Responsible AI controls ensure safety, compliance, and governance across every interaction.
Together, this ecosystem enables organizations to move beyond isolated chatbots toward scalable, secure, and enterprise-ready AI systems, supporting multi-agent collaboration, clear responsibilities, controlled system access, and consistent policy enforcement.
Don't be Totally Irresponsible, use Copilot the right way!
~Hosted with lived intelligence, common sense, and empathy~
As Copilot rapidly becomes part of everyday work, many organisations struggle with a simple but critical question:
How do we enable Copilot safely, responsibly, and at scale—without slowing innovation?
We focus on "responsible usage", not just technical deployment. You’ll learn why successful Copilot adoption requires clear guardrails around security, data privacy, and compliance—and why these guardrails must be communicated clearly to users to prevent shadow AI usage.
We will connect Microsoft Responsible AI principles to real-world organizational practices, showing how responsibility must be embedded in identity, access, and data boundaries so that Copilot reasons only over content users are authorized to see.
The session also explores the human side of responsible AI: leadership endorsement, continuous education, and the importance of shared guidance that explains why certain AI tools are allowed or restricted.
Rather than theory, this session provides practical insights you can apply immediately - whether you’re rolling out Copilot today or refining your existing approach—to ensure trust, accountability, and sustainable adoption across your organisation.
From data to decision: building responsible Copilot Studio agents grounded in Microsoft Fabric
As organizations move from AI experimentation to real-world adoption, the focus is shifting from generating answers to enabling trusted, data-driven decisions.
In this session, we will explore how to build Copilot Studio agents that are grounded in Microsoft Fabric, enabling real-time access to enterprise data while maintaining strong governance and control. Rather than relying on static knowledge or unverified responses, these agents leverage Fabric as a trusted data foundation to deliver accurate, contextual, and actionable insights.
But connecting AI to enterprise data introduces new challenges.
How do we ensure agents only access the right data for the right user?
How do we prevent hallucinations when working with live data?
How do we maintain visibility and auditability into what the agent is doing?
Through a practical, end-to-end architecture, we will walk through:
* Connecting Copilot Studio agents to Microsoft Fabric using modern integration patterns (including MCP and connected agents)
* Designing data-aware agents that are grounded, secure, and reliable
* Applying Responsible AI principles such as data governance, least privilege access, and transparency
* Monitoring and controlling agent behavior to ensure trust at scale
By the end of this session, you will have a clear understanding of how to move from data to decisions—building AI agents that not only work, but work responsibly in real enterprise environments.
From Unpredictable to Reliable: Designing Responsible AI Systems That Work in the Real World
Over the past several months of building and deploying AI-powered applications, one pattern becomes clear .AI systems rarely fail randomly. They fail in predictable ways, but those patterns are often hidden beneath layers of abstraction.
Rather than approaching Responsible AI as a policy layer, this session frames it as an engineering discipline , focusing on how systems behave under real conditions, how failures surface to users, and how to design for reliability, transparency, and control.
Attendees will gain a deeper understanding of common AI failure patterns, learn how to reason about system behavior, and walk away with practical design principles to build more reliable and responsible AI applications.
Operationalizing Enterprise AI Agents with Microsoft Foundry AgentOps
An agent that performs well in a demo may behave differently when models, tools, data, or user behavior change in production.
This session demonstrates how Microsoft Foundry tracing, evaluation, Trace Replay, and Agent Optimizer create a continuous AgentOps lifecycle. Using a production support agent, we’ll trace decisions and tool calls, identify failures, convert real interactions into evaluation datasets, and validate an improved agent before deployment.
We’ll cover quality and safety metrics, regression gates, latency and cost monitoring, human review, and auditability. Attendees will leave with a practical approach for continuously measuring, improving, and governing enterprise agents.
Responsible by Design , Building Reliable Copilot Studio Agents for Microsoft 365"
Extending Microsoft 365 Copilot through custom agents in Copilot Studio introduces both opportunity and responsibility. Without deliberate design choices, agents can produce inconsistent outputs, mishandle uncertainty, and erode end-user confidence in AI-driven solutions.
This session explores the principles and practices of responsible agent design, including structured prompt engineering, uncertainty handling, grounding strategies, and production-grade guardrails. Drawing on real implementation experience, attendees will gain a repeatable framework for building Copilot Studio agents that perform reliably across Microsoft 365 environments and earn long-term stakeholder trust.
Securing Enterprise AI Actions with Microsoft Foundry Toolboxes and Entra Identity
As AI agents move from answering questions to executing business actions, identity becomes a critical security boundary.
This session demonstrates how Microsoft Foundry Toolboxes and Microsoft Entra identity enable governed access to enterprise tools, APIs, and MCP servers. Using an employee-service scenario, we’ll compare user delegation, agent identity, and managed identity while showing how permissions, credentials, and consent remain isolated from agent logic.
We’ll cover least-privilege access, tool governance, auditability, human approval, and Responsible AI safeguards. Attendees will leave with a practical architecture for building agents that can act on behalf of users without compromising enterprise security.
When Demos Fail: Building Trustworthy Copilot Studio Agents with Responsible AI
AI agents powered by Copilot are being adopted rapidly across enterprises. But while building an agent is easy, building one that users actually trust is where most implementations start to fail.
In real-world scenarios, things don’t behave the way demos promise.
Safe prompts get blocked by content filters.
Agents return confident but incorrect responses.
Sensitive data can surface when it shouldn’t.
And most teams are left guessing why the system behaved the way it did.
This session focuses on what it really takes to design responsible AI agents using
Copilot Studio in enterprise environments.
Instead of theory, we will walk through real scenarios where agents fail and break trust,
and how to fix them.
We will break down how Responsible AI shows up across the agent lifecycle:
• Understanding how content filtering actually works and why valid prompts get blocked
• Designing instructions and prompts to reduce hallucinations and unpredictable
behavior
• Choosing between generative AI, topics, and tools based on risk and reliability
• Managing data access, permissions, and governance in Copilot scenarios
• Designing human-in-the-loop patterns for critical business decisions
• Debugging agent behavior and making responses more predictable
This session is grounded in real implementation challenges, not ideal scenarios.
The beating heart of Copilot adoption
~Hosted with lived intelligence, common sense, and empathy~
AI isn't taking your job, but avoiding it might be the real danger, falling behind while others move on.
This tutorial demonstrates a practical, fun, hands-on approach for human-centred cultural change, grounded in common sense and empathy.
It combines technical innovation with people-focused strategies, including Responsible AI Guidelines, the establishment of an AI Council, the vital launch of Copilot Communications, and a pioneering Champions programme.
Get this right, and you have found your "Agent Bosses". Note. A term the speakers hope will have improved by November!
Attendees will hear real-world, proof-of-value success stories (ROI license sweet spots) spanning Retail, Aviation, Hospitality, and more!
We will play with "killer" prompts designed to improve productivity and efficiency!
Bring your Copilot challenges and frustrations, and we’ll work through them together - open debate encouraged (:o)
Sulava MEA co-speakers:
Dr. Khadija Alnofeli, AI Researcher, Academic & Consultant, Abu Dhabi.
Sherina Rendini, AI Skilling Lead & Senior Consultant, Dubai.
Swapna Manikandan, AI Technical Consultant, Dubai.
The Agent That Learns the Runbook :Reliable Agentic Workflows with Foundry IQ and Procedural Memory
Enterprise AI agents often fail at the point where knowledge must become controlled action. Retrieval-augmented generation can ground an agent in the correct documentation, but it does not guarantee that the agent will follow required steps, perform validations, respect approval boundaries, or apply operational policies consistently.
This session presents an enterprise architecture that combines Microsoft Foundry IQ with procedural memory in Foundry Agent Service. Foundry IQ provides permission-aware, citation-backed access to enterprise knowledge across runbooks, policies, architecture documents, and incident records. Procedural memory complements this knowledge layer by extracting reusable execution patterns from audited agent trajectories—capturing when a procedure applies, which actions are required, and which controls must be enforced.
Using an IT incident-management scenario, we will compare a knowledge-grounded agent with one enhanced by procedural memory. The demonstration will show how the agent progresses from retrieving a runbook to executing it consistently while preserving human approval for sensitive actions.
We will also address production considerations including memory isolation, retention and TTL, auditability, access control, observability, and protection against stale or unsafe memories. Attendees will leave with a practical pattern for building governed agents that can transform enterprise knowledge into reliable, repeatable workflows.
Calling For Responsible AI with Azure
Exploring the options of Content safety services in Azure , deep dive on Content Safety Studio and grounding
Orchestrating the data responsibly - Responsible AI with Azure
Understanding the principles of Responsible AI, the global impact of AI , the additional burdens with AI. Different options acialble in Azure . Understanding and using the technology to mitigate the risks of content.Usecase with Powerplatform and Azure AI
Leveraging Azure Content Safety for Ethical AI Development
In this session, we will explore how Azure's Content Safety Services can be leveraged to develop and maintain responsible AI systems. Participants will gain insights into best practices for ensuring AI safety, understand the importance of ethical AI development, and learn how Azure's suite of tools can help mitigate risks such as bias, misinformation, and harmful content. Through practical examples and case studies, attendees will leave with a comprehensive understanding of how to incorporate content safety into their AI projects, ensuring they are aligned with ethical standards and societal expectations.
Responsible AI on Microsoft Azure: Frameworks for Trust, Safety & Compliance
A strategic overview of how Microsoft Azure enables governance, safety, and compliance for AI workloads. Learn how Azure AI Foundry, Content Safety Services, and responsible AI frameworks help organizations build secure and trustworthy AI solutions at scale.
Governance and Assurance for AI-Enabled Power Platform Solutions Using Azure AI Foundry
As organizations accelerate their adoption of AI within the Power Platform, the need for structured governance, responsible AI controls, and enterprise-grade assurance becomes critical. This session provides a strategic and practical view of how to design, deploy, and operate AI-enabled Power Platform solutions with the right safety, compliance, and monitoring frameworks in place.
By the end of the session, attendees will understand how to:
• Apply governance pillars to AI-driven apps, flows, and copilots built on Power Platform
• Leverage Azure AI Foundry for model management, evaluation, and responsible deployment
• Integrate Content Safety Services to enforce safe inputs, outputs, and user interactions
• Build consistent, compliant, and scalable AI operating models for enterprise environments
Content AI with Headless SharePoint with SP Premium
Core Features of SharePoint Premium
Content Experiences (document portals, high-value document solutions, rich file viewers)
Content Processing (AI-driven automation, document assembly, e-signatures, content extraction)
Content Governance (metadata management, retention policies, information protection)
SharePoint Embedded
Detailed explanation of SharePoint Embedded and its capabilities.
How it enables developers to integrate SharePoint features into custom applications.
Real-world use cases and benefits of using SharePoint Embedded.
Live Demo
Demonstrate a practical use case of SharePoint Embedded.
Show how it can be integrated into a custom application.
Highlight the benefits and ease of use.
Building Trustworthy AI: Ensuring Responsible AI with Data Groundedness
In the age of AI, building systems that are not only innovative but also ethical and reliable is paramount. This session delves into the concept of Responsible AI, with a focus on the critical role of data groundedness in ensuring that AI outputs are accurate, reliable, and trustworthy. We will explore Microsoft’s approach to Responsible AI, discuss the importance of groundedness in AI models, and provide practical techniques for testing and validating data to ensure it meets high standards of quality and relevance. Through case studies and hands-on demonstrations, participants will gain actionable insights into building AI systems that are both responsible and robust.
Building Trustworthy AI: Ensuring Responsible AI with Content Safety Services and Azure Foundry
AI is shaping our future faster than ever — but with great power comes even greater responsibility. In this session, let's explore how we can build AI that's not just smart, but safe, responsible, and truly trustworthy.
We'll dive into Microsoft's Content Safety Services — tools that help spot and manage harmful content like hate speech, violence, and self-harm across text and images. I’ll show you how these services can be easily integrated into your applications, helping you create AI experiences that people can genuinely rely on.
We’ll also explore Azure AI Foundry, a powerful platform designed to help you customize foundation models safely. You'll learn:
How Foundry helps with grounded generation and responsible model tuning.
How you can test, evaluate, and deploy AI models with safety built-in — not as an afterthought.
Best practices for bringing transparency, fairness, and governance into your AI journey.
By the end of this session, you'll walk away with practical ways to:
Add Content Safety APIs into your AI workflows.
Leverage Azure Foundry for responsible model development.
Build AI solutions that are ready not just for today's users, but for tomorrow's expectations.
Securing and Moderating your data with Azure AI Content Safety Services
n today's digital world, data security and online moderation are critical challenges. Hate speech, cyberbullying, and inappropriate content can not only damage your brand reputation but also create unsafe and harmful online environments.
This talk will explore how Azure AI Content Safety Services can be your digital guardian, providing you with the tools and insights to:
Identify and remove harmful content: Leverage advanced AI models to detect text and image-based threats like hate speech, nudity, terrorism, and cyberbullying.
Foster a positive online community: Create a safe and inclusive space for your users by filtering out unwanted content and promoting respectful interactions.
Simplify content management: Automate content analysis and flagging, freeing up your resources for more strategic tasks.
Gain actionable insights: Utilize the Content Safety Studio to gain valuable insights into user behavior and content trends, enabling you to make data-driven decisions.
Syntex for your business
1. Intro to Syntex
2. Syntex Capabilities
3. Syntex various training methodologies, pros and cons
4.Demo
Revolutionizing Productivity: A Deep Dive into Co-Pilot Integration with Microsoft 365 Applications
we will explore how Microsoft 365 Copilot can be integrated with digital workforce to enhance productivity and streamline workflows. We will discuss the benefits of using Copilot, its features, and how it can be leveraged to create a more engaged and productive workforce. We will also cover best practices for integrating Copilot with digital workforce and provide real-world examples of successful implementations.
Paper To Data with SharePoint Premium
Delve in to unlock the powerful features of SharePoint Premium in this session to boost collaboration, automate tasks, and streamline content management.To uncover the seamless integration Power Platform to optimize workflows, increase productivity, and unlock valuable business insights from your data,
Moderating your Powerapp content with Azure AI
The importance of content moderation
How Azure AI can be used for content moderation
A demo of content moderation with Power Platform
Elevating Content Safety: Unleashing the Potential of Azure AI in Power Platform Integration
Dive into the realm of digital safety with our session on "Ensuring Digital Well-Being." Discover the dynamic synergy between Azure AI Content Safety and Power Platform as we explore cutting-edge content moderation techniques. Uncover the intricacies of traditional Azure Content Moderation and its integration with Power Platform, offering robust solutions for identifying and mitigating potentially harmful content.
This session is designed for professionals keen on creating secure and responsible online experiences. Explore real-world use cases, best practices, and the latest advancements in content safety technology. Whether you're a Power Platform enthusiast, developer, or IT professional, learn how to implement seamless content safety measures to elevate your digital solutions while prioritizing user well-being. Join us in this exploration of digital guardianship and redefine the standards of content with a live demo
Data extraction using Syntex & ALM of Models
1. Introduction to types of data
2. Form processing
3. Syntex , why is it needed, advantages over form processing
Data extraction using SharePoint Syntex
1. Talk about why Syntex
2. T%ypes of data to address
3. Types of Models available
4. Syntex capabilities
Data extraction using SharePoint Syntex
Various methodologies of data extraction & the best fits for the business
Converting Data to Intelligence with Microsoft Syntex
1. Exploring different types of Data
2. Evaluating the models & best suits
3. Demo
4. Pricing
Content Moderation Using Azure AI
1. Has the details of Moderation API
2. Other Cognitive Services to enhance Moderation
Architecting Solutions with Responsible AI in the Microsoft Ecosystem
As AI becomes deeply integrated into Microsoft 365, Power Platform, and Azure OpenAI, architects must design solutions that are not only innovative but also safe, transparent, and accountable.
This session breaks down the practical application of Responsible AI when designing end-to-end solutions—covering model selection, safety evaluations, prompt design patterns, human oversight loops, red-teaming approaches, and ethical considerations.
With real enterprise scenarios and clear architectural guidelines, attendees will learn how to build AI systems that are trustworthy by design.
Kansas City Microsoft 365 User Group User group Sessionize Event Upcoming
Singapore Microsoft Azure, M365 & Power Platform User group Sessionize Event
AI Community Conference - AICO Dubai Sessionize Event
aMPKL 2025 Sessionize Event
The AI-Native Workplace Summit 2025 Sessionize Event
Global AI Bootcamp 2025 Sessionize Event
Microsoft AI Summit 2025 Sessionize Event
M365 Saturday, Pune 2024 (In-Person) Sessionize Event
Microsoft AI Day 2024 Sessionize Event
Microsoft Talks Academy User group Sessionize Event
Global Power Platform Bootcamp, Pune 2024 (In-Person) Sessionize Event
Global AI Summit 2024 Sessionize Event
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