How Fieldstream rebuilt its data platform for exponential growth and AI adoption

Fieldstream’s original architecture was optimized for speed and rapid iteration. Over time, however, centralized pipelines and shared execution flows began creating operational bottlenecks.

Issues affecting a single customer could impact the entire platform, onboarding took too long, and the growing complexity of marketing data increased manual work and debugging efforts. At the same time, larger enterprise clients demanded stronger guarantees around security, compliance, and data isolation.

Initially, Fieldstream believed the improvements would focus mainly on MLOps. But after working with Astrafy, the team identified that the core challenge was the data platform foundation itself.

“Working with Astrafy has been very efficient, very hands-on, and extremely smooth. The quality of the people involved has been exceptional."

Jens Mathiasson Founder @ Fieldstream

“Working with Astrafy has been very efficient, very hands-on, and extremely smooth. The quality of the people involved has been exceptional."

Jens Mathiasson Founder @ Fieldstream

Astrafy designed and implemented a new architecture on Google Cloud to host, manage and serve Savana’s NLP models. This included setting up a standardized model deployment and inference using Vertex AI, with model registry and consistent serving logic, creating a solid and scalable foundation for current and future models.

To enable external usage, Astrafy built a fully operational API layer. Through API Gateway and Cloud Run, clients can now send clinical documents and receive structured outputs in real time.

The solution includes authentication, quotas, monitoring and logging, turning internal models into a consumable service.

Beyond infrastructure, the architecture was designed for long-term use and growth. Astrafy delivered full documentation, architecture guidelines and enablement, allowing Savana’s team to continue building independently.

The solution is also aligned with Google Cloud standards, preparing it for distribution via the Marketplace.

What began as an internal, service-based use of clinical NLP models has now become a scalable product.

Savana's models are accessible via API for external consumption, allowing clients to send clinical documents and receive structured outputs in real time. This shift also unlocked a new monetization model, with usage-based API access turning what were once internal tools into a revenue-generating service.

Beyond the immediate product, the architecture was built for long-term use and growth, aligned with Google Cloud standards. This positions Savana not only for future scale, but also for distribution through the Google Cloud Marketplace.

“We’ve gotten much more out of the project than we initially assumed, and as a company we are in a much better place now."

Tobias Järlund CTO @ Fieldstream

“We’ve gotten much more out of the project than we initially assumed, and as a company we are in a much better place now."

Tobias Järlund CTO @ Fieldstream