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 redesigned Fieldstream’s pipeline architecture to isolate data and execution environments per client.

Instead of running all workloads through a shared pipeline, each customer now operates within separate execution flows and BigQuery datasets, improving scalability, security, and enterprise readiness.

To reduce manual work and improve operational reliability, Astrafy implemented orchestration with Dagster running on Google Kubernetes Engine.

This enabled parallelized executions, automated workflows, better monitoring, and a more stable onboarding process for new customers.

The platform was modernized on Google Cloud using BigQuery, Google Cloud Storage, Dataform, Airbyte and Argo CD, creating a more scalable and maintainable foundation for future growth and AI workloads.

• Reduced customer onboarding time by several weeks, accelerating time-to-value.

• Improved platform stability and monitoring by eliminating shared pipeline bottlenecks and reducing debugging effort.

• Enabled scalable onboarding of larger enterprise clients.

“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