We Trust AI Agents That Break Every Day - Shy Ruparel, Temporal

Summary

Shy Ruparel explora la brecha entre la adopción de agentes de IA y su implementación real en producción. A pesar de la alta confianza percibida, los sistemas fallan constantemente debido a problemas de gestión de estado, depuración y fiabilidad. A través de un análisis basado en la encuesta 'State of Development' de Temporal, se demuestra que el uso de ejecución duradera permite crear flujos de trabajo resilientes, donde la lógica de negocio y la recuperación ante fallos se manejan sin necesidad de código de compensación complejo, incluso en entornos financieros críticos.

Topics covered

• Adopción de agentes en la industria
• La brecha entre uso y producción

+5 more topics (full content when you follow the channel)

Transcript excerpt

[music] >> All right. Hi everyone. I'm Shay. I am a developer advocate at Temporal. I cannot see anyone in the room. So if you boo me or like want to throw tomatoes or something, I I will have no idea. Um All right. Oop. Clickers are difficult. There we go. I guess I'm not using a clicker today. So agents, they are everywhere. I'm guessing if you are in this room, you are probably building an agent or shipping an agent. Does that sound about right? Yeah. Um so last year KPMG conducted a survey and they figured out that we have seen $3 trillion in terms of corporate productivity gains in 2025 and that's from their agentic AI report. Uh and from that $3 trillion, it's really fin financial services that are leading the way here. So 94% of fintech are saying that AI is core to how their businesses operate and they've decided that AI isn't just a side project, but but it's like it's part of t…