Intelligent Data Decomposition At Scale Using AAVA Agentic AI For A Leading EdTech Company

The client’s monolithic database with over 600 tables and 400 procedures created significant complexity. Redundant and over-leveraged data led to governance and accuracy issues, while mixed reporting and transactional data further impacted system clarity. The modernization effort was also constrained by high cost and long timelines due to manual decomposition efforts. To ensure success, the client needed a phased modernization approach with complete dependency transparency.
We deployed AAVA™, our Agentic AI platform, to accelerate the discovery phase through purpose-built, domain aware Agentic AI workflows that supported both analysis and development tasks.

Microservices Analysis Agent: Parsed microservices to identify service dependencies, endpoints, HTTP methods, request/response payloads, and core business logic

SOA Analysis Agent: Analyzed legacy SOA components to extract database calls, SIBIS wrapper interactions, external service calls, and referenced business class files

Documentation Agents: Assisted developers in generating detailed and standardized service documentation to support downstream engineering and reduce ramp-up time

Unit Testing Agent: Auto-generated JUnit test cases -including positive and negative paths – for targeted services like the Journal Manager Microservice

QE Agent: Began supporting QA teams with Rest Assured test script generation for API validation

This Agentic AI-led approach delivered immediate value in the discovery phase — without requiring intrusive changes to existing systems.

Trusted by Clients. Respected by Partners.

Clients cite strong leadership, responsiveness, and reliable delivery. Partners point to engineering depth, SME coverage, and a steady focus on outcomes over activity.

Business Impact

By embedding intelligent AI agents into the discovery process, the client realized measurable value early -proving the viability of Agentic AI as a key enabler for their modernization roadmap.

Achieved 50–75% time savings across microservices and SOA discovery tasks

Reduced unit test development time by 67%, freeing developers to focus on core logic

Cut documentation and formatting effort in half through AI-assisted wiki generation

Delivered up to 6x acceleration in extracting service metadata, dependencies, and business logic

Accelerated test preparation through automated unit and API test generation

The success of this phase now positions the client to scale automation confidently across the broader transformation initiative in collaboration with Ascendion.

Published

Share

Related Client Outcomes

Insights and Impact

Case Study

Legacy Modernisation saved 45% costs

INSIGHTS

Humans at the Wheel of Agentic Change

Insights and Impact

BSFI Case Study

FinTech Leader Enjoys 40% Faster Digital Service Rollouts

Healthcare Case Study

Medicare Enjoys 60% Faster Onboarding

Insights and Impact

PODCAST

CEO, The Chief AI Officer

INSIGHTS

AI Performance vs. AI That Works

Insights and Impact

HFS Horizon

Ascendion Named a Market Leader in HFS

HFS Horizon

Ascendion Named a Market Leader in HFS

Insights and Impact

PODCAST

The Carbon + Silicon Era

INSIGHTS

Modernizing a 40-year-old banking platform with GenAI innovation