Meetup #16 - Data Modelling & Real World AI

Meetup #16 at Electric Works (in front of the coach station and just up the road from the central train station).

Doors open from 5:30 to give you time to grab a drink and chat to fellow attendees. Talks running from 6 with food provided after the sessions by sponsors Simpsons Associates.

Session 1 - Johnny Winter - Data Modelling for Super Stars! 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.

Session 2- Branden Millward - Agents That Survive Contact With Production: What Breaks Between the Demo and the Real World

Everyone can build an agent that dazzles in a demo. Almost no one talks about what happens at 3am when it loops forever, burns £400 in tokens, or confidently calls the wrong tool against production data. This session is about the gap between the two.

Drawing on real deployments of agentic systems at Intent HQ, I'll walk through the architecture that actually holds up: how to distinguish a genuine agent from a workflow or a chain, and the core patterns tool use, memory, planning, multi-agent collaboration, and human in the loop, that determine whether your system reasons or just rambles. Then we'll get into the parts the demos skip: the failure modes (hallucinations, runaway loops, cost spirals, unreliable tool calls) and the production scaffolding that contains them, observability, guardrails, evaluation frameworks, and security. You'll leave with both the conceptual foundations and the concrete patterns to build agents that deliver value outside a controlled environment, plus an honest map of where agents genuinely excel today and where they still fall over.

Close by 8:30 (with a chance to continue conversations in the Sheffield Tap by the train station)