Problem
Basis’ client Foundation AI, a LegalTech AI company based in the US, processed more than 90 million document pages each month across legal, insurance, and logistics workflows. As adoption of its third-party LLM rapidly increased, the 200-employee company needed a more scalable and cost-predictable AI foundation that could support long-term growth without compromising performance or security.
As part of AWS’s AI Roadmap (AIR) Program, Foundation AI partnered with Basis to modernize its AI infrastructure. Basis leveraged its AWS-native proprietary Bedrock Assessment & Migration (BAM) Platform to assess the client’s AI environment, identify migration opportunities, and develop a data-driven roadmap for migrating its AI workloads to Amazon Bedrock.
Challenges & Needs
Challenges
- Rapid growth in LLM-powered document processing
- Rising inference and operational costs
- Heavy reliance on OpenAI-based workflows
- High-volume document processing workloads
- Long-term platform scalability concerns
Needs
- Scalable AI infrastructure
- Greater model flexibility
- More cost-predictable architecture
- Improved throughput and latency
- AWS-native AI modernization
The Solution
Basis leveraged insights from its proprietary BAM platform to accelerate the planning and execution of Foundation AI’s migration to Amazon Bedrock. BAM evaluated their AI environment, benchmarked Amazon Bedrock foundation models, identified migration priorities, and generated a data-driven migration roadmap, enabling the Basis team to make informed architectural decisions before implementation began.
Using these insights, Basis designed and implemented Foundation AI’s migration to Amazon Bedrock, focusing on scalability, flexibility, and long-term cost optimization. By combining BAM’s assessment capabilities with Basis’ AWS expertise, the team streamlined migration planning, reduced implementation complexity, and modernized Foundation AI’s infrastructure with minimal disruption to existing document intelligence workflows.
Key Solution Components
Primary inference engine for high-volume document classification and extraction workflows with lower latency and reduced operational costs.
Centralized storage for raw document uploads, processed outputs, and training artifacts used across AI workflows.
Fine-tuning of models using Foundation AI’s proprietary document corpus to improve extraction accuracy and reduce prompt complexity.
Real-time monitoring of token usage, latency, and model performance across production AI workloads.
Event-driven orchestration for triggering inference jobs, processing workflows, and forwarding outputs to downstream systems.
The new AWS-native architecture consolidated Foundation AI’s workloads into a scalable environment optimized for long-term growth. Through improved observability, enhanced security, reduced infrastructure costs, and support for future model customization, the solution established a more predictable and resilient AI foundation while enabling them to continue expanding its AI capabilities on AWS.
The Results
Migrating onto Amazon Bedrock helped Foundation AI scale its AI-powered document intelligence platform more efficiently while reducing operational costs and improving throughput. By modernizing its LLM infrastructure on AWS, the company gained greater flexibility, improved observability, and a more predictable cost structure for future growth.
The new architecture also created a stronger foundation for future AI optimization initiatives, including model fine-tuning and workflow automation across high-volume document processing operations.
Technology Leveraged:
-
Lambda
-
Amazon Cloudwatch
-
Amazon S3
-
Amazon Bedrock
-
B.A.M.