Award-winning LMS provider for enterprises and mid-size organizations came to Armakuni for genAI assessment and content pipeline: LLM-powered exam ingestion, zero-ETL analytics, Amazon Bedrock model optimization, DevOps modernization.
The challenge
Armakuni entered through a structured assessment process that mapped DigitalChalk's GenAI readiness from data to deployment. The initial Rapid Assessment SOW funded entirely by AWS at $40,000 grew directly into a flexible engineering PoD engagement. Armakuni now provides a dedicated DevOps resource plus access to application engineers, data engineers, and solution architects across a monthly retainer.
Scale: Enterprise and mid-market LMS customers globally; 8-9 exam question types across diverse content formats (PDF, Word, and more).
What we built
Armakuni delivered genAI assessment and content pipeline: LLM-powered exam ingestion, zero-ETL analytics, Amazon Bedrock model optimization, DevOps modernization. The engagement ran as two SOWs: (1) Rapid Assessment - Tier 2 GenAI Use Case Discovery Assessment; (2) Flexible Engineering PoD - DevOps resource retainer. AWS funded the work at $40,000.
The outcomes
6 measurable outcomes shipped across the engagement. The ones that moved the business the most:
$40,000 assessment delivered at zero cost to DigitalChalk meaning the business received a comprehensive GenAI readiness evaluation, model benchmarking, and a fully scoped implementation plan without committing a dollar of its own budget.
LLM-powered pipeline designed to reduce exam content processing time and standardize question formats across all 8-9 question types.. What previously required manual SME intervention for every content upload is being replaced by an automated ingestion pipeline that normalizes format and structure before content reaches the LMS.
Amazon Bedrock selected as the foundation model layer with flexible model switching built in. meaning DigitalChalk can balance cost and performance across content generation tasks without rearchitecting the pipeline when model requirements change.
Zero-ETL architecture enables real-time analytics without migrating off MySQL. meaning DigitalChalk's reporting and decision-making capabilities expand immediately without requiring a database migration or the disruption that comes with it.
250 hours of engineering capacity per month deployed immediately after the assessment closed with the engagement structure allowing DigitalChalk to shift the skill mix, including data science, ML engineering, or application engineering, as the platform moves from DevOps stabilization into GenAI implementation.
AWS account manager quoted Armakuni's ability to maintain C-suite trust. through a six-month project hold, demonstrating the kind of partnership depth that keeps engagements alive through disruption and positions Armakuni as the team DigitalChalk calls when the GenAI build begins in earnest.
The Armakuni team demonstrated an impressive ability to earn customer trust and deliver against lofty expectations with the customer C-Suite. Ruben and team maintained consistent communication with the customer, even after initial projects were put on hold for half a year.
David Nacson, AWS Account Manager
Built on AWS
Delivered under our AWS Generative AI Services, Data & Analytics Consulting competencies.
What's next
Implementation of LLM-powered content pipeline on Amazon Bedrock; zero-ETL architecture deployment; potential expansion of PoD to include data science and ML engineering resources