Luca Zavarella
Microsoft MVP, Data & AI Solution Hub Lead at Lodestar
Microsoft MVP, Data & AI Solution Hub Lead in Lodestar
Milan, Italy
Actions
Luca holds a degree in Computer Engineering from the Faculty of Engineering of the University of L'Aquila and has more than fifteen years of experience working on the Microsoft Data Platform. He started his experience as a T-SQL developer on SQL Server 2000 and 2005. He then focused on the whole Microsoft Business Intelligence stack (SSIS, SSAS, SSRS), deepening data warehousing techniques. Recently, he has been focusing on the world of Advanced Analytics and Data Science. He contributes to the technical community as a speaker at data events and through his personal blog on Medium. He is the author of "Extending Power BI with Python and R 2nd Ed.", published by Packt Publishing. He holds the role of Data & AI Solution Hub Lead at Lodestar. He is currently a Microsoft AI & Data Platform Most Valuable Professional (MVP).
He also graduated with honors in classical piano from the "Alfredo Casella" Conservatory in L'Aquila.
Luca si è laureato in Ingegneria Informatica presso la Facoltà di Ingegneria dell'Università dell'Aquila e ha più di quindici anni di esperienza di lavoro sulla piattaforma dati Microsoft. Ha iniziato la sua esperienza come sviluppatore T-SQL su SQL Server 2000 e 2005. Si è poi concentrato sull'intero stack Microsoft Business Intelligence (SSIS, SSAS, SSRS), approfondendo le tecniche di data warehousing. Recentemente si è concentrato sul mondo dell'Advanced Analytics e della Data Science. Contribuisce alla comunità tecnica come speaker in eventi sui dati e attraverso il suo blog personale su Medium. È autore di "Extending Power BI with Python and R, 2nd Ed.", pubblicato da Packt Publishing. Ricopre il ruolo di Data & AI Solution Hub Lead in Lodestar. Inoltre, è Microsoft AI & Data Platform Most Valuable Professional (MVP).
Si è inoltre diplomato con lode in pianoforte classico presso il Conservatorio "Alfredo Casella" dell'Aquila.
Area of Expertise
Topics
How regexes in Power BI using Python and R can save your life in extreme cases en
There are cases where cleaning the data provided by a data source requires advanced techniques that are not available by default in the arsenal included in Power Query. In this session we will look at how the use of regular expressions (regex) in Power BI can solve data cleaning situations that are impossible at first glance.
Simplifying ChatGPT: Efficient Document Querying with Azure OpenAI en
This session aims to demystify ChatGPT for a broad audience, highlighting its integration with Azure OpenAI for effective document querying. We'll cover the basics of ChatGPT, its language model, and how to set it up in Azure, focusing on usability, data security, and compliance. Real-world examples will demonstrate its practical applications in extracting insights from data, with the goal of equipping attendees with the knowledge to effectively use ChatGPT in various scenarios.
Enhancing Data Analysis: Leveraging SQL Server's Extensibility Framework with Power BI en
This session focuses on the integration of SQL Server's extensibility framework with Power BI to supercharge your data analytics. We will delve into how to configure and use Python and R engines within SQL Server and explore their applications within Power BI. The discussion will highlight the setup process, the advantages of in-database analytics, and real-world scenarios where this integration shines, particularly in overcoming the limitations of Power BI’s native capabilities. By the end of this session, attendees will have a comprehensive understanding of how to leverage SQL Server's machine learning services to optimize their data analytics workflows in Power BI, ensuring enhanced performance, data security, and usability.
Ask Your Data: Fabric Data Agents in Action en
Fabric Data Agents allow you to ask natural language questions directly to data wherever it resides, whether in OneLake (lakehouse), the Data Warehouse, Power BI semantic models, or even KQL databases. In this session, we'll explore how the agent leverages user credentials (via Microsoft Entra) to query only the data scopes to which it has access, interpret the question, and translate it into queries.
We'll also see how to guide the agent with custom prompts and contextual rules that drive response quality.
An end-to-end demo will move from the authorized dataset to the generated response, demonstrating the complete step-by-step flow.
Ask Your Data in Italian: Fabric Data Agent in Action en it
Fabric Data Agents promise a natural-language interface over enterprise data, but real-world adoption depends on more than just connecting a source. In this session, we'll start with an SQL database in Fabric as our data source and we will walk through what it actually takes to make a Microsoft Fabric Data Agent useful in production: grounding it with the right descriptions, instructions, and example queries; improving answer quality and SQL generation; and enforcing data access through SQL Row-Level Security rather than prompt logic.
We will also address one of today’s most interesting limitations: although English is the only officially supported language, we will show a practical configuration pattern that enables the agent to understand business questions in Italian (or any other language) and answer back in Italian (or any other language) with reliable results. The session is very hands-on and consists almost entirely of a demo showing how to tune the Data Agent based on specific needs.
Chiedilo ai tuoi dati in italiano: Fabric Data Agent in azione en it
I Fabric Data Agent promettono un'interfaccia in linguaggio naturale per i dati aziendali, ma la loro effettiva adozione non si limita alla semplice connessione a una fonte. In questa sessione, partiremo da un database SQL in Fabric come fonte di dati e illustreremo cosa serve effettivamente per rendere un Microsoft Fabric Data Agent utile in produzione: fornirgli le descrizioni, le istruzioni e le query di esempio corrette; migliorare la qualità delle risposte e la generazione di SQL; e applicare l’accesso ai dati tramite la sicurezza a livello di riga (SQL Row-Level Security) anziché tramite la logica dei prompt.
Affronteremo inoltre una delle limitazioni più interessanti del momento: sebbene l’inglese sia l’unica lingua ufficialmente supportata, mostreremo un modello di configurazione pratico che consente all’agente di comprendere domande aziendali in italiano (o in qualsiasi altra lingua) e di rispondere in italiano (o in qualsiasi altra lingua) con risultati affidabili. La sessione è molto pratica e consiste quasi interamente in una demo che illustra come ottimizzare il Data Agent in base a esigenze specifiche.
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