Ever wondered how Salesforce built an end-to-end agentic AI platform that handles everything from creative writing to deterministic financial tasks in a single runtime? In this episode of How to Build Like AWS, we sit down with the developers behind Agentforce to unpack how they built agents that manage the full spectrum — from open-ended creative tasks to precise, rule-based workflows — and why fine-tuning open source models on AWS gives you the "free lunch" of faster, cheaper, and more accurate results. You'll see a live demo building a travel agent using Agentforce Labs, learn how SageMaker HyperPod and Bedrock power their training and inference pipeline, and discover why token explosion in agentic workloads demands a smarter approach to model hosting and cost management. 🔥 What you'll learn: How Agentforce handles deterministic, blended, and fully agentic workflows in one runtime Why fine-tuning smaller open source models beats frontier models on cost, latency, and performance R...