Fabric Data Agent #project
2 items tagged with "project"
📚 Resources
Agentic App with Fabric (incl Data Agents)
Agentic Banking App is an interactive web application designed to simulate a modern banking dashboard. Its primary purpose is to serve as an educational tool, demonstrating: How SQL-based databases are leveraged across different types of workloads: OLTP, OLAP, AI workloads. How agile AI-driven analysis and insight discovery can be enabled via prescriptive data models in Fabric. How easy it is possible to integrate other Fabric workloads (e.g., Report, Data Agent, Notebook) leveraging that data model. Through a hands-on interface, users can see the practical difference between writing a new transaction to the database, running complex analytical queries on historical data, and using natural language to ask an agent to query the database for them.
Fabric Data Agent Demo — Wide World Importers
Two sample Microsoft Fabric data agents built on the WideWorldImportersDW data warehouse. A simple agent with minimal instructions silently returns wrong answers for complex queries, while an advanced agent with full data model documentation handles them correctly — same LLM, same data, different instructions. The demo proves that agent instruction quality is the single biggest lever for accuracy when building data agents over enterprise data warehouses with SCD2 dimensions, bridge tables, and weighted allocations.