Field notes
Notes from our Shopify and software projects. They cover conversion rate optimisation, checkout, Shopify app audits, WhatsApp commerce, cloud architecture and QA automation.
AI Purchase Order Entry for Indian Manufacturers
Turn emailed PO PDFs into sales orders with AI: how extraction works, where SKU matching fails, and why a human check stays in the loop.Read the noteMore field notes
Shopify Multi-Location Inventory for Indian Brands
Warehouses, retail stores and 3PLs on one Shopify store: location limits, how order routing really works, and the setup that cuts split parcels.
Can Indian Shopify Stores Sell Through ChatGPT? What Is Live in 2026
Shopify's agentic storefronts list products in ChatGPT, Copilot, Gemini and Meta. What is live, why buying is open to US shoppers only for now, and what an Indian brand should set up today.
Playwright Test Agents in Practice: Planner, Generator and Healer
Playwright now ships three AI agents that plan, write and repair tests. What each one does, why the healer can hide a real bug, and the review rules we would put around them.
MCP in Production: What to Check Before an AI Agent Touches Real Systems
MCP makes it easy to give an AI model tools. What the MCP specification says about consent, tokens and sessions, and the controls we add before an agent reaches customer data.
Shopify CRO as an Operating Model, Not a Project
Why mature D2C organizations treat conversion optimization as a continuous operating model — and the four systems required to install it.
Production Patterns for AI Integration
Most AI integrations fail in production not because the model is wrong, but because the surrounding system has no contract for evaluation, fallback, or cost governance.
Designing an Enterprise QA Automation Program
Automation programs fail not because the framework is wrong, but because the program lacks an operating model. The four pillars to install before any test is written.