22-25 April 2026 
From Manual Month-End to AI-Powered Finance: Building Self-Service Analytics in Fabric
Proposed session for SQLBits 2026TL; DR
Build production-grade financial reporting in Fabric with enterprise security, quality gates, and AI assistance. Learn medallion architecture for multi-entity data, MCP-accelerated development, and semantic models optimized for both traditional BI and AI agents.
Session Details
Finance teams work with the most sensitive data in any organization, yet they're often stuck in manual, spreadsheet-driven processes.
The challenge isn't just technology adoption—it's about navigating steep learning curves, maintaining governance and control, overcoming IT dependencies, and translating complex finance logic that lives in people's heads or Excel files into scalable, secure solutions. Without a clear strategy, attempting to modernize these manual processes risks creating more technical debt rather than solving the underlying problems.
Microsoft Fabric and Copilot offer a path forward—low/no-code tools that finance teams can own and operate, with AI assistance to accelerate development while maintaining full control. Recent innovations like Model Context Protocol (MCP) servers enable AI agents to help not just design but to actually build and maintain a solution through natural language, dramatically reducing implementation time while preserving governance and quality standards.
In this session, we'll build a complete month-end reporting solution from scratch, demonstrating how finance teams can transform manual processes into AI-powered, self-service analytics.
You'll see how to securely connect to ERP systems and spreadsheets, use AI-assisted notebooks and Copilot to consolidate and transform transactional data, implement medallion architecture (bronze/silver/gold layers) with appropriate security at each stage, enrich data models with the metadata and business context that makes AI effective, and integrate Copilot and Data Agents for natural language financial insights and commentary.
By the end, you'll understand the practical steps to move from manual spreadsheets to a governed, AI-ready finance function—with a clear implementation path that finance teams can execute without having to become data engineers.
The challenge isn't just technology adoption—it's about navigating steep learning curves, maintaining governance and control, overcoming IT dependencies, and translating complex finance logic that lives in people's heads or Excel files into scalable, secure solutions. Without a clear strategy, attempting to modernize these manual processes risks creating more technical debt rather than solving the underlying problems.
Microsoft Fabric and Copilot offer a path forward—low/no-code tools that finance teams can own and operate, with AI assistance to accelerate development while maintaining full control. Recent innovations like Model Context Protocol (MCP) servers enable AI agents to help not just design but to actually build and maintain a solution through natural language, dramatically reducing implementation time while preserving governance and quality standards.
In this session, we'll build a complete month-end reporting solution from scratch, demonstrating how finance teams can transform manual processes into AI-powered, self-service analytics.
You'll see how to securely connect to ERP systems and spreadsheets, use AI-assisted notebooks and Copilot to consolidate and transform transactional data, implement medallion architecture (bronze/silver/gold layers) with appropriate security at each stage, enrich data models with the metadata and business context that makes AI effective, and integrate Copilot and Data Agents for natural language financial insights and commentary.
By the end, you'll understand the practical steps to move from manual spreadsheets to a governed, AI-ready finance function—with a clear implementation path that finance teams can execute without having to become data engineers.
3 things you'll get out of this session
- Implement medallion architecture with financial-grade security: row-level security, column masking, and audit logging across bronze/silver/gold layers.
- Use Agents and MCP servers to accelerate lakehouse deployment, DAX measure development and notebook creation through natural language while maintaining code quality as well as adherence to corporate/industry standards and best practices.
- Integrate Fabric Data Agents (which can be surfaced to MS Teams via Copilot Studio) for conversational financial analysis grounded in actual corporate data/logic (thereby reducing the risk of hallucination!)
Speakers
Rishi Sapra's other proposed sessions for 2026
Data Storytelling in Power BI: From Reports to Narratives - 2026
From Excel to Fabric with AI Agents: Automating Migration with MCP Servers - 2026
From SAP Extracts to AI-Powered Insights with Business Process Solutions - 2026
From Strategy to Execution: Building AI-Ready Data Products with Microsoft Fabric - 2026
Taming the Firehose: Technical Acceleration and ADHD - 2026
Rishi Sapra's previous sessions
What does Microsoft Fabric mean for a Finance/Business Analyst?
For a business team such as Finance, Microsoft Fabric allows you to go from being “IT reliant” to “IT enabled” and this session shows you how!
Whether you’re a data explorer, data analyst, data engineer – or perhaps a newly coined analytics engineer – we will explore what Microsoft Fabric means for you. We will look at the need for the data platform components in Fabric, applied for a finance data use case, and consider the benefits of this being in a SaaS lakehouse architecture. We will also consider how you need to organise your Finance and IT teams to work best with Fabric so that you have the right capabilities to deliver meaningful financial insights at scale.
How to learn fast-changing tech in a post pandemic, Attention-starved world
Struggling to figure out how to learn about new features and pick up new skills in a technology environment that is moving so fast? In this session, Rishi will highlight some key principles of instructional design and how you can use them to become a better learner or teacher!
Power BI Governance: 6 steps to success
Learn how to deploy Power BI at scale within a large Enterprise. The mantra behind this is “discipline at the core, flexibility at the edge” - we will cover deploying appropriate guardrails/controls whilst still retaining the notion of “self-service” within the organization.
Storytelling With Data
Learn how to present arguments with data to effectively communicate the insights you need to get across
Tips and Tricks for working with Finance Data in Power BI
<p>Excel has always been the tool of choice for the finance team with the flexibility it provides for logic, formatting and presentation of numbers. But this flexibility has also caused Governance nightmares, performance issues and huge risks with manual processes. Is it possible to also achieve the desired outcomes and flexibility with Power BI whilst also having all the benefits of working in a more controlled, automated and feature-rich environment? Yes!
In this session Rishi will show how you can have your finance cake and eat it, showing how to build dynamically formatted financial statements , waterfall charts and KPIs in Power BI to tell an engaging story with finance data.
The Incidental Business Analyst (BA) – Designing a Finance Power BI Data Model to Tell a Story
Join this session to learn the key steps in designing a data model: Know Your Audience (KYA), Complete a Scoping Template, Define the data granularity/scope and design a conceptual model. We will use time-tested methodologies based on Kimball Data modelling techniques, including a Bus Matrix and Starnet, complete with templates available for you to freely download.