Back to Console
work

AI Driven Customer Insights Analysis

Event-driven Agentic pipeline analyzing 10k+ weekly tickets for root-cause insights.

Stack
AWS LambdaSQSLangChainRAGDynamoDBGemini API
Links
Architected an event-driven Agentic pipeline (AWS Lambda/SQS) analyzing 10k+ weekly tickets for root-cause insights. Implemented RAG-based compliance workflows to validate agent responses against policy docs, saving 20+ weekly audit hours.

The Challenge

Our product and ops teams were manually analyzing over 50,000 Zendesk support interactions monthly. This process was slow, and we were missing real-time insights into critical customer pain points.

The Solution

I took the initiative to design and build an end-to-end, serverless AI pipeline. I used AWS Lambda and EventBridge to process the interactions in real-time, integrating with the Gemini API to automatically extract, classify, and analyze the sentiment of each customer issue. The data was then stored in DynamoDB.

The Impact

Built a real-time dashboard on top of this data that provided immediate visibility and drill-down capabilities. This empowered our product team to move from slow manual analysis to instant, data-driven decisions, which directly informed our product roadmap and feature prioritization.

System Log End