In this episode, Jesse Zhang joins Raza to discuss building cutting-edge AI agents for customer support. They explore how his early passion for LLMs led to creating a company that’s transforming the way businesses like Rippling, Duolingo, and Webflow interact with customers. Jesse breaks down the challenges of scaling AI systems, the importance of customer feedback, and his predictions for the future of AI.
Chapters:00:00 - Introduction and Jesse Zhang's Background 01:17 - First Exposure to LLMs and Building Early Projects 04:32 - Decagon’s Rapid Growth and Differentiation in AI 06:37 - Understanding Decagon’s AI Customer Support Product 10:21 - Challenges in Building High-Performance AI Systems 13:14 - Evolution from Simple RAG to Agent Architectures 16:54 - Measuring Accuracy with Evals and Customer Feedback 19:05 - Balancing Customization and Reusability Across Clients 22:35 - Handling Customer Data and Incremental Deployment 25:21 - Restructuring Support Teams for AI Integration 27:03 - Team Composition and the Role of Domain Expertise 29:19 - Advice for New AI Builders: Customer-Driven Development 32:21 - Key Insights on AI Agents and Enterprise Adoption 36:34 - Predictions for AI Advancements in 2025 39:41 - Is AI Overhyped or Underhyped? 41:07 - Closing Remarks and Final Thoughts
------------------------------------------------------------------------------------------------------------------------------------------------Humanloop is the LLM evals platform for enterprises. We give you the tools that top teams use to ship and scale AI with confidence. To find out more go to humanloop.com
