Normalized claim
Time: 85% increase
BDM says the approach made analyses 85% faster than manual interpretation and achieved 98% accuracy.
BDM (Big Data Mining) uses Amazon Bedrock to accelerate document processing with LOUIS
Use case typeDocument automationUpdated Jun 13, 2026
Big Data Mining (BDM), founded in Brazil, built LOUIS as a generative AI model to transform document processing across multiple industries. The solution reads and analyzes complex unstructured corporate documents so employees can focus on higher-value work instead of manual document interpretation.
- Organization
- Big Data Mining (BDM)
- Industry
- Finance
- Location
- Brazil
- Published
- May 2026
Reported outcomes
60 seconds
timeTime & speed
+85%time−98%time−40%cost−50%cost
Strategic outcomes
New product / capabilityBuilt an AI document-processing platformNew product / capabilityEnabled large-scale complex document analysisMarket & geographic expansionExtended into insurance and other industriesSpeed & agilityAccelerated document analysis workflows
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Time: 98% decrease
BDM says the approach made analyses 85% faster than manual interpretation and achieved 98% accuracy.
Normalized claim
Cost: 40% decrease
One customer reduced operational effort by more than 40%, equivalent to more than $4.2 million in savings over five years.
Normalized claim
Time: 60 seconds decrease
In insurance, life insurance claims processing was reduced from up to six months to a few minutes, with required data captured in about 60 seconds.
Normalized claim
Cost: 50% decrease
BDM reports saving about 50% in development costs versus building the application from scratch.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Big Data Mining (BDM)
- Provider
- AWS
- Maturity
- Scaled Production
- Linked source
- AWS Solutions Case Study
LOUIS combines computer vision and natural language processing to handle corporate documents at scale, including sensitive formats such as powers of attorney
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 3
- 1Document processing
- 2Claims automation
- 3Workflow automation
- Manually analyzing complex documents consumed substantial employee time and introduced human error.
- In financial services and insurance workflows, document queues and outdated information could delay decisions and create costly rework.
- BDM built LOUIS on Amazon Bedrock to access and customize foundation models.
- LOUIS combines computer vision and natural language processing to handle corporate documents at scale, including sensitive formats such as powers of attorney.
- The solution was applied to a financial institution workflow in Brazil and later extended to insurance and other industries.
- BDM says the approach made analyses 85% faster than manual interpretation and achieved 98% accuracy.
- One customer reduced operational effort by more than 40%, equivalent to more than $4.2 million in savings over five years.
- In insurance, life insurance claims processing was reduced from up to six months to a few minutes, with required data captured in about 60 seconds.
- BDM reports saving about 50% in development costs versus building the application from scratch.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Case StudyPublished: May 13, 2026Publisher: AWS Solutions Case StudyEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
Loading comments...