Building at the intersection of AI and Indian retail.
I'm Kushan Shah, CTPO at Fynd, an AI-native unified commerce platform powering 20,000+ stores across 30 countries. I write about what I learn building AI systems at this scale: agentic development, domain-specific AI for retail, and the infrastructure that connects it all.
20,000+ stores · 30 countries · 300M+ customers served · $2.5B GMV enabled
What I write about
Building with Agents
Real agentic development at enterprise scale: what works, what breaks, and the guardrails I've built.
AI meets Indian Retail
Making AI concrete for Indian retail: channel complexity, demand planning, and what the ground actually looks like.
The Practitioner's Toolkit
Reusable frameworks, Claude skills, open source tools, and workflows worth sharing.
India in Transition
Indian digital infrastructure, geopolitics, and the macro forces shaping tech and commerce.
Recent writing
View all →Security Practices and Tools in the Age of LLMs
How to actually secure LLM and agentic applications in production. Why the model isn't your attack surface, the one rule that predicts agent breaches, and the practices and tools that hold up.
Testing Practices in the Age of Agents
A deep, code-first guide to testing LLM and agentic flows: contract tests, hermetic mocking, statistical gates, LLM-as-judge, multi-turn simulation, and the CI setup that ties it together.
Inside the Claude 4.7 System Card
A practitioner's reading guide to the 200+ page Anthropic document almost no one reads in full. What the launch post hides, where the load-bearing safety numbers live.
Projects
View all →Spec-Driven Dev Template
A template for the /specs directory workflow with CLAUDE.md, verification scripts, and example specs — for teams using Claude Code in production.
Portfolio Analysis Skill
A Claude skill for personal finance portfolio analysis — allocation drift, performance attribution, and rebalancing suggestions from a CSV export.