hr_ops · finance · workflow
PayU builds a secure enterprise AI assistant using Amazon Bedrock with RAG and text-to-SQL agents
PayU employees were relying on public generative AI tools for tasks like troubleshooting, email drafting, and content refinement, creating risks of sensitive financial data—including proprietary system information and regulated documentation—being transmitted to external third-party providers, which conflicted with their compliance requirements as a Central Bank-regulated institution in India.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Employee submits query via Open WebUI
Employees access FMs and agents through the Open WebUI interface, choosing either an FM or an agent from a dropdown menu.
Tools used
Amazon BedrockAmazon Bedrock AgentsAmazon Bedrock Knowledge BasesAmazon Bedrock GuardrailsOpen WebUIAccess GatewayAmazon RDSAmazon EKSAmazon OpenSearch ServiceAmazon S3AWS PrivateLinkApache SparkRAG
Outcome
After rollout, internal estimates showed a 30% improvement in business analyst productivity, with multiple business workflows added to the application, reduced turnaround times, and collaboration between business units accelerating digital transformation.
Results
Time savedreduced turnaround times
Volume30%
Grounding & classification
Source type: technical build writeup
40 fields verified against source quotes, 4 dropped as unverifiable.
agentic workflowai agentconversational aidata extractionenterprise searchragknowledge basepolicy documentbuilder submittedmetric backednamed customerproduction runtime claimedtools describedworkflow describedbankingfinancial servicesemployee productivitytime savedtechnical build writeupback office opsfinance opshr opsagentic task executionextract classify routerag answering