DigitalOcean announced that Workato?s AI Research Lab is using its vertically integrated, inference-optimized platform, accelerated by NVIDIA Hopper GPUs, to advance the development of its next-generation enterprise AI agents while materially improving performance, cost efficiency, and deployment speed. After moving its AI Labs workloads to DigitalOcean, Workato achieved immediate gains for frontier models, including Llama-3.3-70B. To support that vision, Workato AI Research Lab required infrastructure capable of handling distributed training and sustained, reasoning-heavy inference under real production load.
DigitalOcean helped design and tune a distributed inference architecture on DigitalOcean Kubernetes (DOKS). As part of this collaboration, DigitalOcean configured NVIDIA Dynamo to intelligently coordinate workloads across interconnected GPU clusters. By optimizing orchestration around the model and intelligently routing requests across interconnected NVIDIA Hopper clusters, the platform eliminated redundant computation, a primary cost driver for long-context AI workloads.
The result was sustained throughput, significantly faster time-to-first-token, and materially improved price-performance under high concurrency. The integration of the NVIDIA accelerated computing platform with DigitalOcean?s inference-optimized platform unlocks the full potential of production-scale AI. The significant performance gains achieved by Workato highlight the impact of this collaboration.
