BRK247 Breakout Wed 18 Nov 11:30 PST
Token economics: Get more from your production AI budget
Chris Hoder, Kosti Vasilakakis, SukYeon Jung, Alex Tyrrell
Session description
Microsoft's catalogue description
Make every token count with Microsoft Foundry. Learn to match workloads to models and inference tiers, reuse prompt caches, route requests intelligently, and handle capacity limits with smart fallbacks. Hear how WolterKluwer and Enhans optimized token usage to better serve customers. Leave with a practical framework for balancing quality, cost, and latency in production AI.