KOHO — Kortex AI for secure generative AI across fintech workflows

Use case typeCode assistantUpdated Jun 13, 2026

KOHO, a Canadian fintech, built Kortex AI to embed generative AI across internal workflows while maintaining strict data privacy and governance. The solution gives employees and developers secure access to large language models for research, coding assistance, meeting preparation, regulatory compliance, and operational analysis. KOHO uses the platform to improve productivity, accelerate suspicious transaction report processing, and speed up security operations.

Organization
KOHO
Industry
Finance
Location
Canada
Published
June 2026

Reported outcomes

3x

Suspicious transaction report processing speedupTime & speed

1 daysMoney-laundering investigation time reduction−50%Security event resolution time reduction+140%Pull request throughput increase+66%Deployment frequency increase2 daysFeature delivery time

Strategic outcomes

New product / capabilityBuilt secure enterprise AI platformNew product / capabilityEnabled secure LLM access across workflowsSpeed & agilityAccelerated suspicious transaction processingRisk & complianceMaintained strict data privacy and governance

Primary read

Use case focus

Showing 3 of 5

  • 1Enterprise AI platform
  • 2Secure copilot-style assistant
  • 3RAG-enabled internal search
  • KOHO wanted to move beyond isolated AI tools and embed generative AI across workflows.
  • The company needed secure access to LLMs without compromising financial data privacy, logging, or governance requirements.
  • It also needed to support multiple business functions, including development, compliance, and operations, on a scalable AWS foundation.
  • KOHO built Kortex AI on Amazon Bedrock to provide secure, scalable access to generative AI across the organization.
  • The solution uses Amazon Aurora as a vector database to support retrieval augmented generation use cases.
  • Amazon EKS provides container orchestration for AI workflows, APIs, and interfaces.
  • KOHO added centralized authentication, logging, model approval lists, and restricted data-source access to meet financial-services controls.
Technologies
Amazon BedrockAmazon AuroraAmazon EKSAmazon Bedrock AgentCore
  • Suspicious transaction report processing became 3x faster.
  • Money-laundering investigation time was reduced by days.
  • Security event resolution time dropped 50%.
  • Pull request throughput increased by 120-140%.
  • Deployments became 66% more frequent, and a requested feature was built in 2 days.
Architecture

KOHO built Kortex AI on Amazon Bedrock to provide secure access to LLMs within AWS. Amazon Aurora supports vector storage for RAG. Amazon EKS orchestrates AI workflows, API interactions, and user interfaces. The platform includes centralized authentication and logging, model approval lists, and restricted source access to maintain financial-services governance and privacy controls. KOHO also plans to use Amazon Bedrock AgentCore for future multistep agent workflows.

Sources & evidence1
Groundedness: 5/5Type: Customer StoryPublished: Jun 8, 2026Publisher: AWSEvidence: PrimaryConfidence: High
Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases
Customer evidence
More from KOHO
Provider evidence
AWS provider pageAWS ranked cases
Market context
Finance AI use casesFinance industry insightsCanada country insights
AI patterns
RAG
Browse the catalog
All AI use casesAI use-case typesCode assistant use cases

Was this useful?

Similar cases