Field Notes

My Poster at the Google Data Science Summit

Grateful to have had my poster featured at the 2026 Google Data Science Summit in Sunnyvale today.

Autorater Context Enrichment tackles something I've been thinking about for a while: static prompts don't age well. Autoraters built on fixed grounding miss nuance as products evolve, and the data shows it. I explored hybrid RAG and semantic enrichment approaches to make these raters more adaptive, without exploding token costs.

What I loved most about today wasn't the poster; it was the conversations around it. Engaging with the brilliant minds here sparked some great technical discussions that I'm excited to bring back to my work in Voice Experience quality.

A few years ago, I wouldn't have imagined standing next to something like this in a room full of people I look up to. Grateful for the journey, and genuinely excited about what's ahead.

Originally posted on LinkedIn.

Stepping Out of the Deep Work Chamber

When my architect asked for the vision behind the house I'm building in India, I sketched a lighthouse. Five floors. One central column. The bottom floor was a gallery — open, social, collaborative. The top floor was a sealed chamber for uninterrupted deep work. I was low-key proud of

We'd Better Build Some Damn Good Brakes

Waymo is objectively better than an average human driver. Data shows it reduces injury-causing crashes by over 80%. Yet, if an autonomous vehicle makes a single mistake, it's front-page news. We demand near-perfection from machines while accepting massive error rates from humans. And rightfully so. We should apply

No Plan Survives Contact with the Data: Why AI Blueprints Need a Commander's Intent

A few months ago, during a coffee chat, a very smart AI mentor at Google told me something: "The best way to think about these agents," she said,"is like a very smart intern. Give them enough context, define the workflow, and they will execute the code

I Gave My AI Amnesia on Purpose

In 2010, Tom Preston-Werner, co-founder of GitHub, wrote a short essay arguing that engineers should write the README before writing a single line of code. His reason was simple: A perfect implementation of the wrong specification is worthless. A few months ago, I was having an amazing brainstorming session with

Read more

Stepping Out of the Deep Work Chamber

We'd Better Build Some Damn Good Brakes

No Plan Survives Contact with the Data: Why AI Blueprints Need a Commander's Intent

I Gave My AI Amnesia on Purpose