Enterprise Agents Will Compete on Graph Engineering
Enterprise agents need governed relationships between people, data, permissions, memory, and workflows not just better retrieval.
Using AI Agents, Building Systems, and Engineering Leadership
I write about building software, engineering leadership, AI, and what worked in practice.
Start Here
The Hard Part of Building an Autonomous AI Teammate
Building a useful autonomous AI teammate is less about the chat interface and more about routing, trust, memory, governance, and workflow reliability. We built a marketing operator to understand this better.
What Feeding India Taught Me About Engineering Under Constraints
What leading engineering at an NGO taught me about constraints, field research, and small experiments.
The Team That Never Worked Weekends (And Still Shipped On Time)
One team consistently shipped on time without weekend work. Here's what they did differently.
The Org Chart After Agents
As agents move into real workflows, the org chart is coming out with the same boxes and different arrows: who depends on whom, where review time goes, and which skills matter more.
If You're Building Enterprise AI Agents, Start With a Morning Brief
Advice from building enterprise-grade agent systems on why the morning brief is the best first agent to ship, what teams get wrong, and the design rules that make people trust it.
AI at Work Is Mostly a Context Layer
The first useful agent in a company is often the one that reconstructs context and gives people a better starting point.
Engineering Decisions Are Bets, Not Proofs
Engineering decisions are bets under uncertainty. Strong teams optimize for probabilities, learning speed, and reversibility.
Introducing Units - A Tiny DSL for LLM-Generated UIs
A practical look at using a compact UI DSL to reduce LLM token overhead, improve structure validation, and compile cleanly to JSX.
AI Made Everyone “Full-Stack.”
AI has expanded engineers’ reach across the stack but the winners will be the ones who can verify, debug, and operate systems end-to-end.
I Refactored This Blog for UX, Not Vanity
From server-first rendering to no-JS fallback and cross-browser checks.
Powering annotations on articles using LLM
Implementing highlight-to-annotate using WebLLM for in-browser inference.
Build to Outlive
The real measure of engineering leadership isn't what you shipped. It's what keeps working after you leave.
How Over-Reliance on AI Hurts Young Engineers
Vibe coding can create false velocity, and negatively impact young engineers.
Embedded AI Works Better Than Chat For Repeatable Tasks
Chat bots help when goals are ambiguous, but they introduce context switches.
Building Zomato’s Web Platform Team
How I built a cross-functional web platform team while replacing a legacy frontend.
The Leadership Pipeline
What changed when I moved from writing code to building a team that could make decisions without me.
Unpacking Project Failures
Most of our failed projects died from bias and misguided assumptions, not bad engineering.
Using Pkl Language to Generate Configurations
How Pkl Language Improved Our UI Builder.
How Raw User Feedback Saved Our Product (When Dashboards Failed)
We drifted from our users, and our product showed it. Raw WhatsApp messages fixed what dashboards could not.