Skip to content
  • Past event

Tunisia Data Innovation Days

Tunisia

25 July 2026

Saturday

09:00–18:00 local time (GMT+1)

  • Online event

This event took place on Saturday 25 July 2026.

About Tunisia Data Innovation Days

Tunisia Data Innovation Days 2026 is a premier event bringing together data professionals, business leaders, developers, students, and technology enthusiasts to explore the latest innovations in Data, Analytics, AI, and Business Applications.

Through four dedicated tracks, attendees will discover how Microsoft technologies are transforming organizations and empowering data-driven decision-making:

🔹 Microsoft Fabric – Build a modern data platform with unified experiences for data engineering, data warehousing, real-time analytics, data science, and business intelligence.

🔹 Power BI – Transform data into meaningful insights through interactive dashboards, advanced analytics, semantic models, and enterprise reporting solutions.

Read the full description

🔹 Power Platform – Accelerate innovation with low-code tools including Power Apps, Power Automate, and Power Pages to automate processes and create business solutions faster.

🔹 Microsoft Copilot – Unlock the power of AI to enhance productivity, automate tasks, generate insights, and redefine the way people work across the Microsoft ecosystem.

Join us for a day of learning, networking, innovation, and community engagement, featuring expert-led sessions, real-world use cases, live demonstrations, and opportunities to connect with industry leaders and Microsoft technology experts.

Agenda

Times in Tunisia time (GMT+1)

  1. 6:00 PM

  2. 6:50 PM

  3. 7:40 PM

  4. 8:30 PM

  5. 9:20 PM

  6. 10:10 PM

All sessions

Times in Tunisia time

  • 6:00 PM to 6:50 PMMain room

    Microsoft Copilot: Driving Innovation, Productivity, and Responsible Adoption

    Explore how IA including Microsoft 365 Copilot and Copilot Studio are transforming the modern workplace. Learn key AI implementation strategies, best practices for successful adoption, and essential ethical considerations to ensure responsible, secure, and effective use of AI across organizations.

  • 6:50 PM to 7:40 PMMain room

    From Content to Intelligence: Building the Knowledge Layer That Powers AI Agents

    AI agents are only as effective as the knowledge layer that supports them and building that layer requires more than theory. In this session, we dive into the technical foundations that make enterprise content usable for AI‑driven experiences. You’ll explore how knowledge is stored, structured, and accessed across SharePoint sites, OneDrive, and SharePoint Embedded containers, and what those choices mean for authentication, permissions, compliance, performance, and scale. We’ll walk through practical patterns for content modeling, metadata design, and retrieval optimization that improve grounding quality and response relevance. You’ll also learn how these content sources integrate with Copilot Studio, including how agents ground answers, respect security trimming, and orchestrate workflows across Microsoft 365 services. Through live demos, we’ll showcase SharePoint Embedded containers in real-world implementations and highlight tuning, governance, and operational strategies you can apply immediately when building secure, scalable AI‑native solutions. Who should attend: Developers, solution architects, and ISVs designing AI agents and copilots on top of Microsoft 365 content services.

  • 7:40 PM to 8:30 PMMain room

    Microsoft Fabric Governance & Security

    Securing enterprise data requires more than simply granting access—it requires a comprehensive security strategy. In this hands-on workshop, participants will explore how Microsoft Fabric combines platform-level permissions with granular SQL security to deliver robust, scalable, and compliant access control for Fabric Warehouse environments. Throughout the session, we will cover the complete security model, including workspace and item-level permissions, SQL object permissions, and advanced data protection techniques such as Row-Level Security (RLS), Column-Level Security (CLS), Object-Level Security (OLS), and Dynamic Data Masking (DDM). Participants will learn how each security mechanism addresses different business requirements and how they can be combined to implement a layered security approach. Using real-world business scenarios and live demonstrations, we will configure security roles, restrict access to sensitive tables, columns, and rows, hide entire database objects using Object-Level Security, and dynamically mask confidential information without modifying the underlying data. We will also discuss security best practices, governance considerations, and common implementation patterns for enterprise-scale analytics solutions. By the end of the workshop, attendees will have the practical knowledge and hands-on experience needed to design secure Microsoft Fabric Warehouse solutions, implement fine-grained access control, protect sensitive business data, and ensure governance and regulatory compliance while enabling users to access only the data appropriate for their roles.

  • 8:30 PM to 9:20 PMMain room

    Build Power Apps with No Code / Low Code

    Discover Power Apps and build your first application. hands-on workshop where we explore the power of No-Code/Low-Code development with Microsoft Power Platform Whether you're a business user, IT professional, or developer, you'll discover how to quickly build custom apps By the end of this session, you'll have the skills to turn ideas into working applications

  • 9:20 PM to 10:10 PMMain room

    Power BI: From Data to Decision

    This session introduces participants to Microsoft Power BI and demonstrates how raw data can be transformed into meaningful insights and strategic decisions. Participants will explore data preparation, interactive dashboard creation, data visualization techniques, and real-time reporting through practical examples and hands-on demonstrations. The session also highlights how organizations use Business Intelligence to monitor performance, identify trends, and support data-driven decision-making.

  • 10:10 PM to 12:05 AMMain room

    From Prompt to Production: Building Real Agent Systems with LangChain, LangGraph & LangSmith

    Most AI demos work perfectly right up until they leave the notebook. This workshop is about closing that gap: transforming a simple prompt-and-response prototype into a system you can actually trust in production. You'll discover why LangChain, LangGraph, and LangSmith aren't three disconnected tools, but three layers of the same challenge. LangChain provides the building blocks: models, prompts, tools, retrieval, and integrations. LangGraph provides orchestration: branching workflows, loops, parallel execution, state management, and failure recovery. LangSmith provides visibility: tracing, debugging, evaluation, and observability so you can understand what your agents are really doing and improve them with confidence. Drawing on real architectural patterns from a multi-agent educational platform that I designed, built, and defended as my final-year engineering project, including fan-out/fan-in subgraphs and a dual-memory architecture powered by Redis, we'll move beyond tutorials and explore how modern agentic systems are actually built. In this workshop, you'll learn: The distinct roles of LangChain, LangGraph, and LangSmith, where their responsibilities begin and end, and why understanding those boundaries matters. How to use each framework independently and how to combine them into a cohesive production-ready stack. How to design agent workflows as graphs rather than linear chains, and more importantly, how to recognize when graph-based orchestration is genuinely necessary. How to implement short-term and long-term memory, along with the architectural trade-offs between persistence, context, latency, and cost. How to build fan-out/fan-in patterns in LangGraph to execute multiple agent branches in parallel and reduce overall latency. How to trace agent decisions, debug tool calls, and evaluate system behavior with LangSmith, replacing guesswork with observability. How to approach testing and evaluation for agentic systems, where outputs are probabilistic rather than deterministic. The practical challenges involved in moving from a working prototype to a deployable, observable, and maintainable production system. By the end of this session, you'll understand not only how to build agents, but how to architect, debug, evaluate, and operate them in the real world. Because building an AI demo is easy. Building an AI system people can rely on is where the real engineering begins.

Who took the stage

6 speakers shared what they know.

Open the wall

Who made it happen

Every AI Community Day is run by volunteers from its city, with help from the global team.

The local team is not listed yet

The organizers of Tunisia Data Innovation Days appear here once they confirm their place on the event.

Run the next one in Tunisia

Global team

The people who run AI Community Days around the world.

The recap

Tunisia, in numbers.

This event took place on Saturday 25 July 2026. Thank you to everyone who came, spoke, sponsored and volunteered.

  • 6

    speakers took the stage

  • 6

    sessions on the agenda

Got a certificate from Tunisia?

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.

Want another one in Tunisia?

Tell us you would like the next edition, or help organize it with the AICD platform behind you.

Upcoming events

The next AI Community Days.