Enterprise Knowledge Search · Fraud Detection
Vivriti Capital needed to replace a legacy architecture consisting of Amazon Redshift, open source Spark, Airflow and custom orchestration to eliminate pipeline failures, compliance risks and manual engineering interventions across its API-driven lending business.
Reported impact
Reported outcomes include ~25–30% Lower TCO, with reduced cloud, DevOps, and R&D support overhead; ~20% Faster SQL performance and almost no downtime for faster deliverables; ~8 weeks Phased migration with no disruption to lending operations.
Vivriti Capital built its Databricks implementation around Databricks SQL, Databricks Genie, Redshift, Airflow. Vivriti Capital needed to replace a legacy architecture consisting of Amazon Redshift, open source Spark, Airflow and custom orchestration to eliminate pipeline failures, compliance risks and manual engineering interventions across its API-driven lending business. Databricks SQL serves governed analytics, dashboards, and ad hoc queries for business users and operational teams. Databricks Genie lets business users ask natural-language questions over curated data. Redshift represents a legacy warehouse replaced or simplified by the new platform. Airflow represents legacy orchestration simplified by Databricks-native workflows. The solution also connects to Redshift, Airflow, API, so teams can work from a shared governed environment instead of disconnected tools.
Source data is ingested into databricks, curated in shared lakehouse tables, processed with Databricks compute and orchestration services, and served through analytics, semantic search, or model endpoints for downstream users and applications. It connects with Redshift, Airflow, API.
Core workloads (including ~20 workflows and 50+ pipelines) migrated within eight weeks, with development and client validation running in parallel to compress the timeline.
Vivriti also uses Databricks Genie for semantic search and conversational analytics, replacing an in-house text-to-SQL solution built on large language models. By adopting a native capability, the team reduced infrastructure complexity and
~20% Faster SQL performance and almost no downtime for faster deliverables
~25–30% Lower TCO, with reduced cloud, DevOps, and R&D support overhead
~8 weeks Phased migration with no disruption to lending operations
“It was a fast, predictable, and well-orchestrated journey,” said Alagu Bala Kumar Narayanan, VP of Architecture and R&D.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
OpenAI Sample Mar 6, 2025 Nubank Nubank needed to scale employee knowledge access, customer support, and fraud-response quality across more than 114 million customers without slowing response times or overloading human agents. 70% reduction in chat response times AI Assistant · GPT-4o · GPT-4o mini 
Microsoft Sample Jan 8, 2025 Aditya Birla Capital It wanted to streamline the business and deliver a more connected customer experience using generative AI. Financial services provider Aditya Birla Capital has a massive market presence with more than 40 million… Azure AI Search · Azure AI Services · Azure Cosmos DB Microsoft Sample Jan 11, 2024 MONETA Money Bank Customer center MONETA Money Bank built by NTT Czech Republic uses an AI-driven voicebot, powered by Feedyou Platform and Microsoft Azure AI, to converse fluently in the complex Czech language, and can gather customer… As a result, the bank cut call center operational costs by 10 percent, while increasing customer satisfaction. Azure AI Services · Azure AI Speech · Azure Machine Learning 
