Serverless AWS Setup for AI Claims Platform

“bespinian has been a key partner from the very beginning. They helped us to launch our MVP in the cloud in just three months after founding amaise and have since supported us in turning it into a scalable, secure, reliable platform, used internationally for processing highly sensitive medical documents”

Markus Baumgartner, CTO

Customer

amaise is a Bern-based insurtech company that has developed an AI-powered claims intelligence platform for the insurance industry. The platform helps insurers resolve bodily injury claims faster, more accurately, and at lower cost by analyzing complete case files, not just medical records. amaise’s agentic AI technology turns unstructured medical and legal documents into actionable insights, enabling claims teams to achieve up to 84% efficiency gains and significantly faster settlement times. The company serves major Swiss insurers including Mobiliar, Baloise, Dextra, and Coop Rechtsschutz, and is expanding internationally.

Background

As an AI-first company processing sensitive insurance data, amaise required a cloud infrastructure that could handle complex AI workloads while maintaining the flexibility to iterate quickly on their product. The team needed to focus on developing their core AI capabilities rather than managing infrastructure, and required a foundation that could scale with their growing customer base across Switzerland and beyond.

Building AI pipelines that process thousands of pages of medical and legal documents demands a robust, scalable architecture. At the same time, as a startup, amaise needed to keep operational costs under control and minimize the burden of infrastructure maintenance.

Project Goals

The collaboration focused on establishing a solid technical foundation:

• Set up initial AWS infrastructure for applications and AI pipelines
• Design an architecture that minimizes operational overhead and costs
• Ensure flexibility to adapt as the product evolves
• Provide ongoing infrastructure reviews to maintain best practices

bespinian’s Role

bespinian supported amaise in building and optimizing their cloud infrastructure on AWS.

Initial Infrastructure Setup

We helped amaise establish their foundational AWS infrastructure for both their customer-facing applications and their AI processing pipelines. By adopting a serverless-first approach, we designed an architecture that automatically scales with demand while eliminating the need to manage servers.

Serverless Architecture

The serverless approach was central to the infrastructure design. This architecture allows amaise’s AI workloads to scale elastically based on processing needs, whether handling a single document or thousands of pages across multiple claims. When not in use, costs drop to near zero, making this particularly valuable for a growing startup.

Infrastructure Reviews

Beyond the initial setup, bespinian conducted multiple reviews of amaise’s infrastructure as their platform evolved. These reviews ensured that the architecture continued to follow AWS best practices, identified optimization opportunities, and addressed any emerging security or performance concerns.

Technologies Used

• Cloud Platform: Amazon Web Services (AWS)
• Architecture: Serverless
• Infrastructure as Code: Terraform