Michigan .NET Users Group (MI .NET)

Agenda

• 5:30 - 6:30pm Networking
• 6:30 - 7:30pm Presentation
• 7:30 - 7:45pm Closing

Abstract
AI agents are everywhere - but how do they actually work in a real data platform?

In this session, we’ll go beyond chatbots and build a practical, enterprise-ready multi-agent system using Databricks Agent Bricks. You’ll see how structured data (SQL tables, Delta Lake, Genie Space) and unstructured documents (PDFs, invoices, call logs, reviews) can be orchestrated through a supervisor agent to answer complex business questions.

Using a realistic enterprise demo, we’ll walk through:

• Extracting invoice data from PDFs and images into structured tables
• Grounding answers in product manuals and compliance documents
• Analyzing customer sentiment from call transcripts and reviews
• Routing tasks across specialized agents using a supervisor
• Connecting everything back to SQL analytics and dashboards

This is not theory — this is a working architecture that connects your existing SQL data estate to modern AI workflows.

If you work with SQL, data engineering, or analytics and want to understand how agentic AI fits into the real enterprise stack, this session is for you.

Bio
Mou Rakshit is a Senior Manager of Data, AI & Analytics Engineering at Accenture/Avanade and a Principal Data & AI Solution Architect specializing in building modern, unified, AI-ready data platforms using Microsoft Fabric and Databricks. She leads enterprise-scale data strategy and platform architecture initiatives that enable organizations to move from fragmented analytics environments to governed, high-performance lakehouse ecosystems.

Her work focuses on designing scalable medallion architectures, implementing robust governance models, enabling real-time intelligence, and operationalizing AI and advanced analytics across the enterprise. Mou bridges executive strategy with hands-on technical execution, ensuring that modern data platforms are production-ready, resilient, and aligned to business outcomes.

She holds a Master of Science in Computer Science from Wayne State University and a Master’s in Health Services Administration from the University of Michigan. A Databricks Champion and frequent industry speaker, Mou shares practical frameworks and real-world lessons on architecting unified data foundations that power AI at scale.

Agenda

• 5:30 - 6:30pm Networking
• 6:30 - 7:30pm Presentation
• 7:30 - 7:45pm Closing

Abstract
Many healthcare organizations live in a world of hybrid systems: half modern APIs, half legacy apps. Instead of replacing everything, what if you could connect and structure the data you already have?

This session explores how to unify siloed systems through smart metadata, semantic layers, and dependency-driven queries. You’ll learn strategies to evolve existing systems gradually—without downtime or total rewrites.

Bio
John Sly is a software developer and data engineer specializing in large-scale ETL systems and healthcare data integration. With over a decade of experience in PHP, PostgreSQL, and enterprise data workflows, he bridges legacy architectures with modern, automated solutions that improve reliability and transparency. His talks focus on practical engineering—what really works when moving complex data at scale and delivering something impactful at the end.

Agenda

• 5:30 - 7:30pm Holiday Party

Details
Join this joint event for a festive Holiday Party! Connect, unwind, and celebrate the season with fellow members. Food, drinks are available for purchase directly from the restaurant. Feel free to bring your favorite board games.

Agenda

• 5:30 - 6:30pm Networking
• 6:30 - 7:30pm Presentation
• 7:30 - 7:45pm Closing

Abstract
You have seen the five-minute demo where an AI writes an app and the room claps. Here is what nobody demos: what happens when you try to take that app from 90% to 100%. That last 10% is where AI-written code fights you, forgets its own architecture, and quietly breaks in production.

The gap between the demo and the job is not the model. It is your process. The guardrails are the process.

I have been driving AI coding agents in production since 2023, and I run a team that ships real software with them every day. We turned a 20-year-old VoIP platform into an AI-forward company from the inside, and a contributor fresh out of college took one of our products to production and kept it there, with happy customers, on the exact loop I will show you.

I walk that loop step by step: documentation and context first, steering with rules and skills, small explainable turns, two-pass review, disciplined integration. The loop does not care which agent you drive; it works the same with GitHub Copilot, the Microsoft Agent Framework, Cursor, Claude Code, or Codex. You will meet the failure that lurks at each step (the refactor death spiral, leftover mock data, a silent broken contract with a vendor) and the guardrails that caught each one before a customer did.

Then I show the real setup live: Claude Code turning a meeting transcript into a shipped change, a roster of senior engineers encoded as skills a junior can summon on demand, and the MCP servers that feed the agent live context.

You will leave knowing the difference between vibe coding and agentic engineering, when each is the right call, and the one change to make Monday to ship AI-written code you actually trust.

Bio
Mike Onslow is an accomplished executive blending business acumen with technical expertise to drive innovation and strategic growth. As the CTO at Clarity Voice and co-host of the Artificial Antics podcast, Mike explores how AI and business strategy intersect to solve real-world challenges. With extensive experience leading cross-functional teams, managing cloud platforms, and fostering a culture of quality and inclusivity, Mike excels in aligning technological vision with business objectives. Passionate about advancing diversity and agility in the tech industry, he empowers organizations to thrive in today’s tech-driven landscape.