- Past event
AI Community Day Mahdia
Mahdia, Tunisia · In person
14 February 2026
Saturday
08:00–17:00 local time (GMT+1)
Village Des Langues
Rejiche, MahdiaOpen in Google Maps (opens in a new tab)
This event took place on Saturday 14 February 2026.

Mahdia, Tunisia · In person
14 February 2026
Saturday
08:00–17:00 local time (GMT+1)
Village Des Langues
Rejiche, MahdiaOpen in Google Maps (opens in a new tab)
This event took place on Saturday 14 February 2026.
AI Community Days Mahdia - Bringing AI to the beautiful coastal city of Tunisia.
💻 Online Rooms (Microsoft Teams)
Main Room
https://teams.microsoft.com/meet/34233053626529?p=NMEfxt0tPX9KBsAZoD
Room 2
https://teams.microsoft.com/meet/35435782456469?p=tzZw2HaCfK8mKBChPQ
Workshop Room
https://teams.microsoft.com/meet/38040497251945?p=QsNKz6CQzKF3wF18MR
Times in Mahdia time (GMT+1)
9:00 AM
9:30 AM
10:00 AM
10:55 AM
11:45 AM
12:00 PM
1:50 PM
2:35 PM
3:20 PM
Times in Mahdia time (GMT+1)
Cette session présente comment Microsoft Fabric, en synergie avec Power BI, permet de construire une plateforme analytique unifiée de bout en bout. Les participants découvriront une approche moderne allant de l’ingestion des données à la visualisation interactive, avec un focus sur la simplification des architectures BI, la performance et la prise de décision rapide grâce à des cas concrets.
This hands-on workshop teaches participants how to build, orchestrate, and deploy multi-agent AI systems using Google's Agent Development Kit (ADK) and Vertex AI Agent Engine. Attendees will learn how to create AI agents powered by Gemini models, build custom tools, and implement sequential, iterative, and parallel workflows. The workshop explores design pattern trade-offs, agent architecture decisions, callbacks and observability, memory management, and scalable deployment. It is structured around 10 progressive Jupyter notebooks and concludes with a full-stack capstone project deployed to Google Cloud using Agent Engine for agents and Cloud Run with a React and FastAPI stack for the frontend and backend. ✅ Who is this workshop for Developers, AI engineers, cloud practitioners, and technical professionals who want a practical introduction to building and deploying multi-agent systems. 🎯 Key takeaways • Build and orchestrate multi-agent AI systems with Google ADK • Create custom tools and coordinate agent teams powered by Gemini models • Choose between LLM-driven and workflow-driven design patterns (Sequential, Parallel, Iterative) • Navigate agent architecture trade-offs: Sub-agents vs. Agent as a Tool • Implement callbacks, observability, and guardrails for production readiness • Master session management, state, artifacts, and short-term vs. long-term memory • Deploy production-ready full-stack AI systems on Google Cloud (Agent Engine + Cloud Run)
Artificial Intelligence is everywhere in organizations — but not all AI use cases bring the same value, risks, or operational impact. Without a clear framework, teams struggle to decide where to apply AI, how to prioritize efforts, and how to avoid wasted experimentation. In this talk, I introduce VIP.CLAUD, a practical matrix I designed to classify real-world AI usages based on delivery impact, decision-making value, and operational complexity. Through concrete examples drawn from program execution, delivery management, and AI agents adoption, we will explore: why many AI initiatives fail to create sustainable value, how to distinguish useful, dangerous, and illusory AI use cases, how to use VIP.CLAUD to guide teams, leaders, and organizations toward better AI decisions. This session is designed for practitioners looking for clarity, structure, and actionable insights, not hype.
Tired of repetitive tasks? Want to streamline workflows and boost productivity? Join this hands-on workshop to learn how to automate processes effortlessly using Microsoft Power Automate! What You'll Learn: The basics of automation and Power Automate How to create flows to automate tasks across apps and services Connecting to Microsoft 365, SharePoint, Outlook, and more By the end of this session, you'll be ready to eliminate manual work, save time, and focus on what matters most, all with the power of automation
Microsoft Fabric builds powerful AI models and model development, while AI Foundry breathes life into these models through deployment, evaluation, and integration. Together, they offer a comprehensive, enterprise-grade AI lifecycle.
Cette session technique présente comment automatiser la création des demandes d’achat dans Dynamics 365 Finance en exploitant Copilot Studio, Microsoft Teams, Power Automate et des prompts IA. Vous découvrirez comment orchestrer un processus conversationnel, sécurisé et extensible, permettant aux utilisateurs de générer des demandes d’achat directement depuis Teams ou Copilot, avec parsing intelligent des données, gestion des lignes multiples et intégration native à D365 Finance via OData. La session inclut une démonstration pas-à-pas, des conseils de gouvernance et des bonnes pratiques pour l’industrialisation.
AI development has rapidly evolved from basic model experimentation to systems capable of executing generated code, invoking tools, and interacting with real infrastructure. While this progression unlocks powerful new capabilities, it also introduces significant risks—particularly during local development, where untrusted or AI-generated code often runs directly on developer machines. This session presents a practical, end-to-end approach for safely building and running AI workloads using Docker and Azure. We will begin at the local development stage, demonstrating how Docker Sandbox enables isolated, ephemeral environments for executing AI experiments, generated scripts, and agent-driven workflows without compromising the host system. This setup allows developers to iterate quickly while maintaining strong safety and reproducibility guarantees. Next, the session will illustrate how the same containerized AI workloads can transition seamlessly to the cloud using Azure Container Services, such as Azure Container Apps. Attendees will learn how to integrate containerized applications with Azure AI services, including secure access to managed AI models, while applying best practices in identity management, networking, and observability. Beyond the tools, the session will emphasize responsible AI development, including the importance of isolation boundaries, controlled execution, cost awareness, and governance, from local experimentation to production deployment. A live demonstration will showcase the full lifecycle—from sandboxed local execution to cloud deployment on Azure—highlighting how containers create a consistent and trustworthy path for modern AI systems. This session is designed for developers, cloud architects, and AI practitioners seeking practical strategies to confidently move AI projects from experimentation to production.
This session is designed for business users, developers, and administrators, including PowerApps, SharePoint, and Azure developers. It will guide you in selecting the most effective storage solution for your development project, whether you're creating in-house applications or purchasing from ISVs or Microsoft. A detailed checklist will be provided to ensure you choose the most suitable storage option for your needs before starting your project. The solutions discussed will include SharePoint Embedded, SharePoint Document Library, and Blob Storage. Each solution will be evaluated based on various requirements, with an in-depth examination of working with SharePoint Embedded. The session will emphasize the significance of data for your company and projects, highlighting its role in informed decision-making, problem-solving, and process improvement. Security and compliance aspects of each storage solution will also be covered, ensuring your data is protected and meets regulatory standards. Furthermore, the cost implications of each storage solution will be analyzed, aiding you in making budget-conscious decisions. The session will also explore how AI and Copilot agents can enhance your storage strategy, from automating data management to improving data analytics. By the end of this session, you will have a clear understanding of the optimal storage solution for your needs.
Drowning in documents 💁♂️? Let's fix that. This session reveals how to transform Microsoft 365 into your intelligent document powerhouse—automating the tedious stuff so your team can focus on work that actually matters. What You'll Walk Away With: 🔹Forget theory. It'll be all about demos, demos and more demos! 🔹Generate documents instantly. Master content assembly techniques that turn SharePoint list data into professional documents—contracts, reports, letters—populated automatically from your templates. One click, done. 🔹Get signatures without the runaround. Integrate e-signature capabilities directly into your Microsoft 365 workflows. No third-party apps, no email chains, no chasing people down. Just seamless digital signing that tracks and stores everything properly. 🔹Stop manually tagging documents. Set up column autofill to extract and populate metadata automatically. Dates, document types, reference numbers—let the system handle it while you do literally anything else. 🔹Break language barriers effortlessly. Deploy built-in translation capabilities that convert documents across multiple languages automatically. Your global teams get content in their language without sending files to translation services. 🔹Make everything searchable. Leverage OCR (optical character recognition) to extract text from scanned PDFs, images, and legacy documents. That mountain of paper you digitized? Now it's fully searchable and usable. 🔥This isn't about shiny features—it's about reclaiming hours every week, reducing errors, and building document workflows that scale. Whether you're processing invoices, managing contracts, or wrangling compliance documents, you'll leave with a clear roadmap to implementation.
Microsoft Copilot is rapidly evolving from a conversational assistant into a foundation for agentic AI—systems that can reason, plan, and take autonomous action across enterprise workloads. In this session, we move beyond prompts and chats to explore how cognitive agents can be architected using Microsoft’s AI and Power Platform stack. You’ll learn how to design agentic AI solutions that combine Copilot Studio, Power Automate, Microsoft 365, Dataverse, and Azure AI to create intelligent agents capable of understanding intent, orchestrating multi-step workflows, and operating securely within organizational boundaries. What this session covers Understanding Agentic AI How agentic and cognitive agents differ from traditional copilots and chatbots, and where they deliver real enterprise value. Copilot as a Platform Using Copilot Studio and Microsoft 365 Copilot extensibility to build task-aware, context-rich agents. Agent Architecture & Design Patterns Planning, memory, tool-calling, orchestration, and human-in-the-loop patterns using Power Platform and Azure AI. End-to-End Agentic Workflows Designing autonomous workflows that span SharePoint, Outlook, Teams, OneDrive, and line-of-business systems. Governance, Security & Responsible AI Applying enterprise controls, data boundaries, auditing, and compliance while enabling intelligent autonomy. Who should attend Solution Architects & Technical Leads Power Platform & Microsoft 365 Professionals AI Engineers & Innovation Teams Enterprise IT & Digital Transformation Leaders Key takeaways A clear mental model for agentic AI architecture in Microsoft technologies Practical patterns to move from Copilot experiences to autonomous agents Guidance on when (and when not) to introduce autonomy A roadmap to scale agentic solutions responsibly across the enterprise
11 speakers shared what they know.

Delivery Leader at Ledger - Agile, GenAI & Large-Scale Execution
Spoke in Mahdia
Solution Architect Microsoft Dynamics 365 FinOps Apps
Spoke in Mahdia
M365 Architect, Cyclotron
Spoke in Mahdia
AI Hub I Power Platform Architect | Digital Transformation | Solution Architect | Microsoft AI Copilot | Project Manager | Delivery Manager | O365 | SharePoint | Power BI |COE Starter Kit
Spoke in Mahdia
Senior Developer Advocate | Microsoft MVP Microsoft 365 & SharePoint | International Speaker | Community Leader | Product Evangelist
Spoke in Mahdia
MSc SE| Microsoft MVP | MCT | PSPO | PSM | Tech Lead @Cyclotron
Spoke in Mahdia
Cloud Solutions Architect, Speaker, Book Author, Trainer, Docker Captain
Spoke in Mahdia
Quantum Technology Inc
Spoke in Mahdia
AI/ML Solutions Engineer & Consultant
Spoke in Mahdia
Founder of SimpliTraining and MCT Trainer
Spoke in Mahdia
Microsoft Certified Trainer | CHAFROUD.NET
Spoke in MahdiaEvery AI Community Day is run by volunteers from its city, with help from the global team.
The organizers of AI Community Day Mahdia appear here once they confirm their place on the event.
Run the next one in MahdiaThe people who run AI Community Days around the world.

CEO · Cloud and Security Architect

Cloud and AI Engineer · Tech Trainer · Tech HealthCare Expert · Women in Tech Advocate

Chief Information Security Officer at FORTEIA

AI, Microsoft 365 and Power Platform Architect · MCT and MVP · Trainer · Speaker

Founder & Independent Technical Consultant · Microsoft Certified Trainer (MCT) · Power Platform, M365, AI & Copilot

Solution Architect on Microsoft Dynamics & AI
The recap
This event took place on Saturday 14 February 2026. Thank you to everyone who came, spoke, sponsored and volunteered.
11
speakers took the stage
10
sessions on the agenda
Every certificate has a unique code. Anyone can check that it is genuine on our verification page, and you can add it to your LinkedIn profile from your account.
Tell us you would like the next edition, or help organize it with the AICD platform behind you.
Partners
We work with them at every AI Community Days event, in every city.
Upcoming events
Nov 24–25
.NET Africa Conference 2026