World Congress 2025 Aug 20, 2025 Session details

Data Analytics with Microsoft Fabric: End-to-End Use Case with Data Agents

Dr. Alexander Wachtel , Hanna Schwab

Eliminate fragmented data pipelines by centralizing your architecture with Microsoft Fabric. See how conversational AI data agents extract operational insights directly from OneLake without complex SQL.

Pause
Mute Enter Fullscreen
#1 about 2 min

Introduction to Microsoft Fabric and data agents

Setting the stage for exploring Microsoft Fabric capabilities by outlining session goals and core data concepts.

#2 about 2 min

Traditional data architecture before Microsoft Fabric

How disjointed legacy environments necessitated the patching of multiple disparate services for data ingestion and visualization.

#3 about 1 min

Unifying services with the Microsoft Fabric platform

Consolidating disparate pipelines into a single platform accelerates deployment and simplifies unified user access management.

#4 about 2 min

Centralizing disparate data storage with Microsoft OneLake

Adopting a unified data lake approach centralizes scattered file systems and database schemas without painful custom integrations.

#5 about 3 min

Introducing conversational queries with AI data agents

Navigating unstructured database syntax hurdles by utilizing natural language interfaces mapped directly against complex internal storage.

#6 about 2 min

Pharmaceutical inventory and demand forecasting use case

Managing complex buying criteria effectively through continuous visibility into shifting inventory allocations and pending wholesale demands.

#7 about 1 min

Integrating enterprise business applications for unified analytics

Overcoming operational silos by streaming diverse business applications continuously into a universally accessible analytics architecture.

#8 about 1 min

Syncing transactional updates through live database mirroring

Mirroring SQL databases eliminates risky batch export delays by cascading external pricing adjustments into the ecosystem instantly.

#9 about 1 min

Building modern data pipelines for legacy exports

Translating bulky legacy customer system exports seamlessly into high-performance Delta tables for scalable analytic pipelines.

#10 about 2 min

Tracking dynamic inventory levels with real-time intelligence

Eliminating asynchronous storage blind spots to guarantee machine learning algorithms consume accurate, real-time localized inventory counts.

#11 about 2 min

Forecasting product demand using Azure Machine Learning

Anticipating sudden purchasing trends natively using embedded machine learning notebooks that identify statistically probable stock depletions.

#12 about 2 min

Accelerating data exploration with conversational AI queries

Bypassing steep database querying learning curves by interacting intuitively with datasets using casual language questions.

#13 about 3 min

Configuring system prompts and schema metadata contexts

Correcting artificial intelligence hallucinations by explicitly declaring structural metadata mappings and specialized internal geographic abbreviations.

#14 about 2 min

Analyzing top products and granular production costs

Verifying system prompt stability by processing multipart questions regarding overlapping manufacturing costs and regional inventory fulfillment.

#15 about 1 min

Publishing custom data agents to Azure Foundry

Scaling custom analytical contexts out uniformly by binding local data agents into overarching Azure AI instances.

#16 about 3 min

Current preview limitations of AI data agents

Working around preliminary release limitations restricting agent behavior from performing advanced time-series analysis or broad schema scans.

#17 about 3 min

Best practices for building a proof of concept

Validating new cloud architectures decisively by focusing exclusively on isolated initial proof-of-concept deployments before broad scaling.

Matching moments

4:20 min

Connecting data and modern AI with data fabric architecture

Andreas Christian · LIVE

2:36 min

Defining data fabric for modern data integration

Andreas Christian · LIVE

40 sec

Introduction to building real-world AI agent solutions

Dennis Zielke Dennis Zielke +1 · WWC 2025

1:13 min

Managing AI development with Azure AI Foundry

Ricardo Ricardo · WWC 2025

3:44 min

Building durable AI agents with Microsoft agent framework

Stas Lebedenko Stas Lebedenko · WWC Europe 2026

4:21 min

Scaling operations using Azure AI Foundry tools

Maxim Salnikov Maxim Salnikov · WWC 2025

Upcoming sessions on this topic

Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

Databases in the Agent Era

Monica Sarbu

Founder and CEO of xata.io

Monica Sarbu
Open session

World Congress 2026 North America

When Agents Became Users: Rearchitecting Identity and Permissions for AI at Scale

Dor Cohen, Yoav Gal

Dor Cohen
Yoav Gal
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit
Open session

World Congress 2026 North America

DeepAgents: Build Multi-Agent AI Systems That Actually Work

Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

Anagha Rumade
Anjana Umapathy
Apoorva Jaiswal
Open session

World Congress 2026 North America

Agents That Own Their Inference: Building Production AI Agents on Dedicated GPUs

Duan Lightfoot

Sr. AI Engineer, Akamai

Duan Lightfoot