Senior Technical Program Manager · Enterprise Consulting

Enterprise AI,
from the trenches.

I'm Nattu — I run complex, large-scale delivery programs at a global consulting firm. On the side, I run my own AI experiments to figure out where these tools actually add value in enterprise contexts. This is where I write about what I'm learning: what worked, what didn't, and what nobody's talking about yet because they're too busy polishing the demo.

Read my writing → About me

Agent Evaluation Jun 2025

If You're Validating a Customer Service Agent, Here's How I'd Approach It

3 tiers, 24 measures, a hard safety gate, and a triage system for figuring out not just that something failed — but why, and what to fix.

Test Automation · Architecture May 2025

One Way to Generate Test Cases Using Agents — A RAG + Few-Shot Approach Worth Exploring

Exploring a RAG + few-shot prompting pattern for test case generation — with a feedback loop that gets smarter over time. Partly built, partly hypothetical, fully worth thinking about.

About Nattu

I'm a Senior Technical Program Manager at a global consulting firm, where I lead large-scale, complex delivery programs. Alongside that work, I run independent AI experiments to understand where these tools genuinely change enterprise outcomes — and where they don't. This site is where I document those explorations honestly.

Enterprise AI, from the trenches.

Latest Writing

If You're Validating a Customer Service Agent, Here's How I'd Approach It

One Way to Generate Test Cases Using Agents — A RAG + Few-Shot Approach Worth Exploring

About Nattu

Enterprise AI,
from the trenches.