Experimentation & A/B Testing

A Simple A/B Stats Calculator for You

It’s been a while since my last post on Navigating A/B-Seas , but I was prodding myself to be back, doing the thing I enjoy the most - writing. Over the weekend, I decided to roll up my sleeves and bring to life a small side project I’ve been meaning to build for some time.

Introducing:AB-Sea Stats

Why AB-Sea Stats?

In the world of experimentation, numbers tell stories. But too often, we get bogged down in the calculations instead of focusing on the insights. AB-Sea Stats is my humble attempt to help analysts, data scientists, and decision-makers sail through these complexities with clarity and confidence. Whether you’re planning experiments or analyzing results , this app brings the tools you need right to your fingertips.

What can the v1 of AB-Sea Stats do for you?

1. Statistical Significance Calculator

Designed for when you need to determine if your test results are significant.
Ideal for proportion-based metrics like click-through or conversion rates.
Outputs include: Proportion difference, Confidence intervals, p-values and z-values.

2. Power Analysis:

Helps you plan experiments efficiently by calculating: Sample size required for different effect sizes (MDEs), Time (in weeks) to reach those sample sizes based on your weekly traffic.
Supports mean-based metrics (e.g., revenue, time on site) and proportion-based metrics (e.g., success rate).
Flexibility to choose between absolute and relative metrics for your effect size.

App in action

Set Sail with AB-Sea Stats

Building AB-Sea Stats was a refreshing way to combine my love for statistics and experimentation with a desire to create tools that simplify everyday workflows.

This is just the start! More features are on their way in the coming weeks, and your feedback is the wind in my sails. Let me know how the app works for you, what features you’d love to see, or just drop a comment if it helped simplify your workflow. What would you like to see added? What’s been a challenge for you when it comes to A/B testing or experiment planning?

Check it out here: https://ab-sea-stats.streamlit.app/

Originally published 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

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

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