Publications & Articles
14 notesThinking and writing about systems, architecture, AI, and the decisions behind building software for regulated environments.
Discover the four critical architectural layers of an enterprise AI harness. Learn how integration gateways, state management, execution sandboxes, and audit spines turn raw AI models into secure, reliable digital workers.
Working in a distributed system without TraceIDs is like navigating a maze in the dark. Learn how to build the Ubiquitous Telemetry Pattern for enterprise scale.
Context is working memory; Memory is what persists. Discover the architectural tiers of AI memory, from simple Markdown routing to Agentic RAG and learn how to stop re-teaching your AI every session.
AI is like a microwave. It's an incredible piece of technology, but we still don't cook every meal in it. An architect's perspective on why we need to stop force-fitting AI into broken systems.
In Enterprise AI, a harness is the software infrastructure wrapped around a language model that turns it from a raw text generator into a functional, reliable AI agent. A popular industry shorthand defines this relationship simply: Agent = Model + Harness.
Enterprise AI isn't an LLM problem. It's a data governance crisis. Learn how architects solve RBAC, PII, and data residency to deploy secure AI at scale.
India's digital economy runs on billions of SMS messages every day. Explore the architecture, reliability challenges, and future of OTP authentication
Five years from now, users won't care whether a feature uses an AI agent, MCP and RAG. They'll simply expect the software to work.
Most developers default to the strongest AI model for every task. Here’s why treating AI models like a specialised engineering team leads to faster iterations, lower token costs, and better software development.
Why It Matters and Why Enterprise Adoption Will Take Years. The HTTP QUERY method solves one of REST’s oldest design problems.