Fabric Agentic AI for BI and Business Focussed Data Modelling
Details
Location: iO Associates, St Bartholomew's House, Bristol BS1 2NH.
Sponsored and Hosted by iO Associates (Tech & Digital recruitment specialists), we bring you an evening of Data and Networking.
AGENDA
18.00 – 18:25 Meet & Greet
--------------
18:25 - 18:30 Introduction & Welcome
Welcome, and thanks to our sponsors
--------------
18:30 - 19:15 Talk: Fabric Agentic AI for BI by Prathy Kamasani
Agentic AI can now understand a requirement, model the dimensions, wire up the relationships, write the DAX, and generate the PBIP files, but only if you know how to brief it and how to check its work. I'll walk through what agentic BI development actually looks like in Microsoft Fabric: an AI agent building a real semantic model and report from a written spec, with the corrections that build genuinely needed along the way.
The interesting part isn't the prompt. I'll cover the parts that make agentic development reliable: writing a spec an agent can act on without guessing, setting a quality bar before the agent starts, and reviewing agent output properly rather than taking it on faith. The example uses an open dataset, including a mistake the agent made and what that revealed about the spec.
You'll leave knowing what to check before you trust an agent's semantic model, and where it still needs a human in the loop.
--------------
19:15 - 19:45 Pizza and Networking
--------------
19:45 - 20:30 Talk: Business Focussed Data Modelling by Johnny Winter
How to collaboratively design your star schema with end users.
Despite claims to the contrary, dimensional modelling and star schemas are alive and well the in the modern data world. But whilst developers might have great technical skills and understand how to build a star schema, they may lack the business domain knowledge to ensure that what they deliver is fit for use by analysts and self-service users. On the flip side, these end users often know what they want and need from a data platform, but struggle to explain this in a way that makes it easy for developers to implement.
How can we improve the requirements gathering process to make sure we avoid the tensions that can arise from this?
This session will cover a data modelling requirements approach that looks to bridge the gap between business and IT by using an end-to-end process for working with business users to collaboratively design a dimensional model, making sure you build super star schemas and turn your self into a data modelling superstar.
--------------
20:30 - Social/Pub
---
Speaker Bios
Prathy is a Microsoft MVP and the solopreneur behind Data Nova, a Power BI and Microsoft Fabric consultancy and training provider, with 15 years across the Microsoft data platform. You'll usually find her organising the London Microsoft Fabric User Group or speaking at events like SQLBits and FabCon.
www.data-nova.io | LinkedIn | YouTube
Johnny is an independent data consultant who has been working with Business Intelligence software since 2007, specialising in full stack data platform development since 2016. He’s a self-confessed data nerd, and as well as running Greyskull Analytics, he runs a blog on Substack and has a YouTube channel where he likes to geek out about all things data. He's passionate about the data community and since 2023 has been a co-organiser of the Power BI & Fabric Manchester User Group.
greyskullanalytics.com | LinkedIn
----
Photos
We ask that you do NOT take photos at this meetup.
We will invite people to be included in a group photo/s during the event. Speakers will let you know if it's okay to photograph their presentation (excluding other attendees).
You may see organisers taking photos during the talks. These will be of speakers, if they have agreed to this, and will not include faces of attendees.
