Skip to content
Vamshi Jandhyala

AI Lab

Experiments and prototypes.

A working portfolio of small, opinionated explorations in what enterprise AI products need to become reliable enough for regulated institutions to act on: the data agents draw on, the tools they act through, and the guardrails around them. Each one starts from a product question, refusal and evaluation, observability, entitlements and lineage and cost, and is built as the cheapest artifact that makes the answer legible. Each has a writeup of what it was testing and what fell out, and most have a clickable demo.