Projects | Naveen K — AI Systems Engineer

Projects

Systems work, product experiments, and architecture case studies.

This is less a portfolio grid and more a set of notes on problems worth solving, the shape of the architecture, and what changed in practice.

Featured system

A document intelligence system for insurance workflows that combines OCR, LLM extraction, confidence checks, and human review.

Problem: Manual extraction from premium and loss summaries was slow, inconsistent, and expensive. Analysts spent 15 to 30 minutes per document while backlogs kept growing.
Architecture: A staged pipeline handles ingestion, layout analysis, OCR, semantic extraction, confidence scoring, review routing, and structured persistence. The system is optimized for reliability over raw model theatrics.
Impact: Processing time dropped to a few minutes per document, accuracy improved materially, and the output became useful for downstream reporting instead of a manual re-entry task.

The project that clarified how I think about agentic systems: useful when scoped well, observable, and grounded in enterprise constraints.

Problem: Teams wanted AI everywhere, but without shared primitives the result would have been duplicated integrations, weak controls, and expensive one-off systems.
Architecture: The platform centered on reusable workflow primitives, specialist agents, guardrails, and a thin product layer for each use case. The emphasis was governance and repeatability, not hype.
Impact: It created a foundation for additional AI use cases, shortened the path from experiment to deployment, and helped establish a more credible internal AI operating model.