Thursday
Room 2
13:40 - 14:40
(UTC+11)
Talk (60 min)
Designing AI-Powered Backends with Azure OpenAI: Reliable, Structured, and Production-Ready
In this session, I’ll demonstrate how to build reliable, production-ready AI backends using Azure OpenAI Service—moving beyond chat interfaces to implement AI-driven business logic that performs intelligent micro-operations inside your applications.
We’ll explore patterns for generating machine-readable, structured outputs (JSON, key/value payloads, classifications, and entity records) with strong control, validation, and reliability. Using a real example, I’ll show how AI can identify existing entities to prevent duplicate creation and maintain data integrity across a system.
Attendees will learn practical techniques, prompt patterns, token management, and architectural approaches for turning Azure OpenAI into a predictable and safe backend service that can allow you to plug in Intelligence into any part of your system.
Mark Tinderholt
Mark is an experienced technologist whose journey began in application development, spanning web and client-server applications to sophisticated distributed systems and microservices. Along this path, he developed deep expertise in automation and DevOps, leading diverse project teams and guiding cloud practice organizations through strategic, operational, and pre-sales leadership roles. Currently, Mark holds a hands-on engineering position at Microsoft, contributing directly to the Microsoft Azure platform.
Beyond his professional work, Mark shares his passion for cloud computing through his YouTube channel, "The Azure Terraformer." He is also the author of "Mastering Terraform," a practical, multi-cloud guide to Infrastructure-as-Code covering AWS, Azure, and Google Cloud, and has created the Udemy course "Terraform 101."