Žiga Vaupot's Blog

Posts

Unlocking Oracle Analytics Cloud with AI: Oracle Analytics Cloud MCP Server

Unlocking Oracle Analytics Cloud with AI: MCP for Oracle Analytics The Challenge: Bridging gaps between AI and Enterprise Analytics Over the last year or so, we’ve seen a major shift in how we understand and use analytics systems—especially in the enterprise world. Modern BI platforms have grown more capable, and AI models have matured at an incredible pace. Expectations have evolved with them. Users now want answers instantly, workflows that feel effortless, and insights that surface proactively, not after a dozen filters, clicks, and exports. Oracle Analytics has already embraced this direction with features like Insights and the AI Assistant, which bring intelligence directly into the analytical experience. These tools help users explore data more intuitively, explain trends in plain language, and flag anomalies before they become issues. They’ve raised the bar for what “AI in analytics” should look like. ...

HROUG 2025: ML & AI meet Oracle Analytics

Between 15th and 18th October 2025, I had the opportunity to speak at the HROUG 2025 conference, held on the beautiful island of Crveni otok (Red Island) near Rovinj, Croatia. The event brought together Oracle professionals and enthusiasts for several days of workshops, presentations, and community networking. During the conference, I delivered a workshop titled ML/AI Meet Oracle Analytics where I explored how Machine Learning and Artificial Intelligence integrate within Oracle Analytics to unlock deeper insights and smarter decision-making. I wanted the session to be practical and hands-on, showing how we can move from descriptive dashboards to predictive and even generative insights without ever leaving OAC. Oracle Analytics and AI — A Natural Partnership Over the past few years, Oracle Analytics has evolved far beyond being just a visualization tool . It’s now a platform that doesn’t just display data — it helps interpret it. Some of the key features addressing this area are:...

Automn MakeIT 2025: Graphs - the bridge between data and generative artificial intelligence

The Autumn MakeIT 2025 Conference event took place on October 14th, 2025 , at the Computer Museum in Ljubljana . Its unofficial theme, NO SLIDES, JUST CODE ,” truly captured the spirit of the day. The sessions were delivered by four Slovenian Oracle ACEs — Zoran Tica, Lucas Hirschegger, Urh Srečnik, and Žiga Vaupot. While Zoran and Lucas focused on development within Oracle APEX , Urh and I explored some of the exciting intersections between Oracle database technologies and artificial intelligence . My session was — quite literally — my first deep dive into graphs and Oracle’s support for Property Graphs . As promised, there were zero slides — my goal was to explore how property graphs can be leveraged in a GraphRAG (Graph-based Retrieval-Augmented Generation) scenario. That’s why my presentation carried the title: Graphs – the Bridge Between Data and Generative Artificial Intelligence . It’s no secret that I built upon all the resources I could find on this topic. My primary re...

Semantic Model Series 9: Data Fragmentation

What is Data Fragmentation? Data Fragmentation in Oracle Analytics refers to the practice of dividing large datasets into smaller, logically separated segments—called fragments —based on defined criteria such as time, region, or product category. This technique is primarily implemented in the semantic layer to optimize query performance and data management. By configuring fragmentation content filters on multiple logical table sources, Oracle Analytics can intelligently route queries to only the relevant data source, reducing processing time and improving efficiency. Fragmentation is especially useful in large-scale deployments where data is physically partitioned or spread across multiple tables or databases. Just to clarify, when speaking of data fragmentation in Oracle Analytics, we’re not referring to table range partitioning, which is managed entirely at the database level and does not require any configuration in the semantic model, as partitioning is handled automatically ...

Semantics Modeler Series 8: Using Data Filters to enable Row-Level Security

Using Session Variables in Row-Level Security Setup Dynamic row-level security is essential for scalable and maintainable data governance. It allows data access to be tailored automatically based on the current user’s context, improving security while simplifying administration. Instead of hard-coding filters for each user or report, dynamic security ensures that as the user base grows or changes, the security model adapts seamlessly without requiring manual updates for every report or subject area, enhancing both performance and user experience. In our first test example, we saw that we can use Session Variables for filtering analyses and reports based on a dynamic value dependent on the current user. However, it doesn't make much sense to create these filters every time on each report or analysis. It is a much better idea to implement filters in the model itself. This results in implicit filters on all reports, without the need to create filters explicitly. Applying row-...

Semantic Model Series: 7. Variables

In Oracle Analytics Semantic Modeler, variables play a critical role in customizing and controlling Analytics behavior at runtime. There are three main types of variables: Session Variables Global Variables Static Variables A global or session variable's initialization block contains a default initialization query that is run to initialize or refresh the variables defined in the initialization block. The initialization query references the data source's tables that supply the variable values. A query can populate values into several variables, with one variable for each column in the query result. A static variable's initialization block doesn't contain an initialization query. To define a static variable, you specify the variable name and value directly. Session Variables Session Variables are dynamic variables set per user session, typically at login or when a report is run. They help personalize content, enforce security, or pas...