The Hidden Engineering Behind Production AI

The Hidden Engineering Behind Production AI Everyone can build an AI demo. Getting one into production is a very different challenge. Over the last year Head for Data have been building an AI-native support platform, integrating large language models into an operational workflow used by real engineers handling real customer requests. The interesting part wasn't choosing the model - it was everything else. In this talk Colin Parry will walk through the engineering decisions that don't make the headlines: protecting sensitive data before it reaches an LLM, designing reliable event-driven architectures, collecting user feedback, testing AI systems whose behaviour changes over time, and deploying changes safely into production. Along the way he will share practical lessons from a real client engagement: including the mistakes they've made, what surprised them most, and why successful AI systems are usually won or lost outside of the model itself. Whether you're building AI products, leading technical teams or simply curious about what production AI really looks like, you'll leave with a clearer understanding of what it takes to move beyond proof-of-concepts. Speaker Bio Colin is the Head in Head for Data with a BSc in Applied Physics and an MSc in Renewable Energy. He has been working with data for over 18 years, starting his career analysing wave and wind data for several renewable companies before supporting the BI system at Aggreko and becoming their first data scientist with a focus on predictive maintenance. He then moved to become Director of Data Science at a carbon reporting platform, analysing millions of energy meter data points from commercial buildings, where his work received several patents. He founded Head for Data in 2023 and strongly believes that data and AI is there to empower businesses to do more with less, making better decisions and improving employee output. We will have this talk and Q&A. Michael Young, CEO @ MBN will be the chair.