Excited to share something I’ve been working on at Scale AI recently: enabling long-running enterprise agents. Earlier this week, we open-sourced Agentex to support these advanced enterprise use cases. And today on the blog, Jason Yang and I published a new tutorial that showcases the advanced capabilities of Agentex by walking through how to build an advanced procurement agent based on a real customer workflow. In it, we walk through the technical architecture that makes long-running, reliable agents possible and why durability will be critical for the next generation of enterprise AI. Check it out at the link in the comments. Huge thanks to Maxim Fateev, Ethan Ruhe, and the team at Temporal Technologies for collaborating with us on this work. Bonus: Jason and I will be demoing the tutorial and talking through the technical details live on Thursday, Nov 20. Register below!
Tutorial and blog: scale.com/blog/agentex-temporal-tutorial
Impressive work. Long-running, durable enterprise agents are exactly what the next era of AI infrastructure needs — reliability, memory, and continuity over complex workflows. Agentex combined with Temporal’s orchestration is a powerful foundation for building agents that can operate across real business processes rather than isolated tasks. This is the direction that will unlock true enterprise-grade AI. Excited to explore the architecture you shared and to see how these long-running agents reshape procurement and other mission-critical operations. Great collaboration from both teams 👏
Daniel Miller Prieto how are you handling the cost of running agents that sleep for weeks then wake up? most companies building 'long running' agents quickly realize that keeping workflows alive for months is expensive at scale. curious if you're seeing that with real customers or if the procurement agent is still mostly a demo.
Agentex isn’t just another framework — it’s a signal of what enterprise AI must become. Durability transforms agents from short‑lived helpers into long‑term collaborators, embedded in real workflows. Open‑sourcing this architecture means the foundation for the next generation of enterprise AI is now shared.
There is a precise moment in any transformative work where the line of brilliance becomes unmistakable — and in this announcement by Daniel Miller Prieto, that line is clear and sharp. Agentex is not merely an engineering achievement; it is a strategic inflection point. The architectural maturity, the obsession with reliability, and the elegant integration with Temporal show a level of thinking that separates innovation from industry-shaping intelligence. This is exactly where the future of enterprise AI is being drawn — with discipline, durability, and vision. Exceptional work, Daniel. A masterclass in technical clarity and strategic foresight.
The future of enterprise AI lies in reliability and long-term agent performance. Agentex seems like a game-changer for advanced use cases, making AI more durable and practical for everyday business needs.
It’s been great to work with you and the rest of the Scale team!
Congratulations on the launch of Agentex! This is a significant advancement for enterprise AI solutions. Looking forward to the demo.
Webinar registration (or to receive the recording): exchange.scale.com/public/events/agentex