Key highlights
>95 percent
success with accurate and fast replies
6
extra territories chosen for solution expansion
Challenges
A luxury retailer with outlets across Europe wanted to explore gen AI in HR operations.
The goal was to enable employees to self-serve and find answers to HR queries independently.
Solution
AWS-native zero-ETL pipelines, a three-tier Redshift architecture with data sharing, Airflow-based orchestration, automated MLOps runbooks, and cost-optimized DevOps
Zensar partnered with the customer team to operationalize an AWS-first architecture with Zero-ETL ingestion and curated Redshift layers. Data sharing bridged BI, EDL, and food demand clusters, giving analysts secure, near-real-time access without physical data movement. Airflow orchestrated multi-account pipelines with parameterization, alerts, and metadata-driven execution. MLOps standardized model deployment via a Kedro runbook, integrating CI/CD and operations. Return-leg pipelines captured forecasts from partners. EMR, Glue, and SQL jobs were optimized to cut execution times by 50%+. Cluster RPUs were right-sized (128 → 64), and lower environments were shut down when idle, achieving ~50% cost savings.
1
Developed a generative AI-powered HR chatbot proof of concept (POC) on Azure infrastructure using Azure OpenAI's large language model.
2
Integrated 68 HR policy documents from the UK into the system.
3
The chatbot provided accurate answers to HR policy questions, referencing source documents.
Impact
App performance
The People team rated the app highly, confirming it addressed most employee queries.
Policy gaps
The POC identified policy document gaps, prompting HR to address them.
Phase two POC
A second-phase POC, incorporating HR documents from seven countries, is under client consideration