Žiga Vaupot's Blog

This is a summary blog post with references to posts published under the Oracle Analytics Meets AI theme. In this series, I am looking at how AI capabilities are becoming part of the Oracle Analytics experience: from asking questions in natural language, to using AI directly inside workbooks, and then extending the experience with more focused AI Agents. 1. Talk to Your Data with Ask BI 2. From Workbook Assistant to AI Agents

Oracle Analytics Meets AI: From Workbook Assistant to AI Agents Ask BI brings a conversational experience to search. The next step is to bring that experience closer to the analytical work itself - inside a workbook, and eventually as a reusable, purpose-built assistant. Oracle Analytics offers both an AI Assistant and AI Agents . They share the same basic goal: help users ask questions of governed data in natural language. The difference is in where they live and how much context they can carry. The AI Assistant is embedded in a workbook. An AI Agent is a standalone object that can be configured with data, instructions, and knowledge documents. That distinction is useful because not every analytical conversation needs the same level of specialization. The AI Assistant: conversational analysis in a workbook The AI Assistant is accessed from the Auto Insights icon in a workbook. It gives users a chat interface to ask questions and explore the workbook’s data. It can work with ...

For a long time, searching in an analytics platform meant finding an object: a workbook, a dashboard, a dataset, perhaps a visualization someone had already created. That remains useful, but it is not always where an analytical question starts. Often the question comes first: What was revenue by brand in 2023? Then comes the next question: Drill into BizTech and show sales by line of business. And then another: Focus on Communication and compare sales and profit by region. This is the experience that Ask BI , available from the Oracle Analytics search bar, is designed to support. It lets users search for content and ask questions of prepared data in the same place. Rather than treating a request as a route to one existing report, Ask BI can turn it into an interactive analysis that evolves with the conversation. Search is becoming an analytical starting point The familiar search bar is an excellent entry point because it is already where users go when they do not know exactl...

I recently deployed Oracle AI Database Private Agent Factory (OPAF) v26.4.0 on OCI as part of my internal demo and prototyping environment. The goal was straightforward: stand up a Knowledge Agent that could ingest documents and answer questions using OCI GenAI. What I got instead was a frustrating series of database deadlocks that took most of a day to fully resolve. Here is the full story — including every dead end — so you do not have to repeat it. The Setup OPAF runs as a Podman container on an OCI compute VM in the Frankfurt region. My initial database choice was an Autonomous Database 26ai Free tier instance, which seemed reasonable for a demo environment. OPAF version: 26.4.0.0.0 Container: oracle-applied-ai-label / Podman VM: agentfactoryvm3, OCI Frankfurt Database initial: AutonomousDB23ai — ADB 26ai, Free tier LLM: OCI GenAI, meta.llama-3.3-70b-instruct, eu-fran...

In my previous blog posts, we explored this fascinating new technology— how to set it up , the broader analytics paradigm it introduces, and a deep dive into some specific Oracle Analytics functions. But what about the basics? What about standard business reporting—the business-as-usual activities we deal with every day? For example, the classic financial reports that managers rely on daily to run the business. These are the standard reports that are typically pre-prepared and embedded within dashboards. Well, let's take a look! I have tested two examples of those standard financial reports : Revenue analysis report that compares current year actuals vs. previous year, vs. planned data and calculates year-to-date values. Performance report that is providing information about revenue, profit and profit margin for the selected period, ie. half-year. The process is already known by now. Startup Claude client and start asking questions. When working with OAC MCP Server, ...