Blog

Engineering insights, AI strategy, and lessons learned building with emerging technology — from the people doing it.

Building in Public — Many of these posts are dispatches from building shilpiworks.com (production AI agent platform) and Understanding Dementia (free guidebook + 200-concept Knowledge Portal). Filter by “shilpiworks” or “dementia” to read the full stories.

Featured Latest Post
Browse by topic:

Recent Posts

15 posts · Page 1 of 2

With AI, the Same Five People Can Be Five Teams of One

September 23, 2026·Arun Batchu & Claude (AI)·10 min read

Handoffs belonged to an age of specialists. With AI, one capable person can carry a piece of work through every role, and the person who can do it is a multipotentialite whose main skill is learning a new field fast. The handoff worth keeping is the one that checks the work.

Read the full post

Stop Training. Build a Learning System.

May 2, 2026·Rick Tanler·5 min read

The half-life of a professional skill is now under five years. Annual training cycles cannot keep pace. The companies that lead in five years will be the ones that built a capability stack — not a course catalog.

Read the full post

Notes on Physics-Informed Neural Networks: A Projectile Experiment

May 1, 2026·Sharat Batra, PhD·7 min read

Eight noisy measurements. A neural network that has never seen a downward arc. And yet — when Newton's second law is embedded into the loss function — the model predicts the apex, the asymmetric descent, and the landing point within centimeters. A 49× improvement that points to where ML is heading in physics-constrained domains.

Read the full post

Loosely Coupled, Tightly Integrated: The Microservices Principle as the Org Shape AI Demands

April 24, 2026·Arun Batchu, David Quimby·5 min read

The most adaptive software systems of the last twenty years are loosely coupled and tightly integrated. The most adaptive organizations of the next twenty will be the same. The microservices principle separates operational coupling from interface integration — and that separation is the org shape AI leverage actually demands.

Read the full post

The Faster-Horse Trap in AI Adoption

April 18, 2026·Megan C. Starkey, David Quimby, Rick Tanler, Arun Batchu·4 min read

Most organizations deploying AI today are breeding faster horses — bolting LLMs onto existing workflows to claim a win without changing anything. The automobile shift has not happened yet, and the Ford quote everyone misquotes shows why.

Read the full post

Your AI Assistant Should Know What Page You're On

April 15, 2026·Arun Batchu·5 min read

Most embedded AI assistants are context-blind — same generic answers whether you're reading about GPU architecture or dementia care. The fix isn't better prompts. It's situational awareness.

Read the full post

Research Trapped in Documents Doesn't Compound

April 15, 2026·Arun Batchu & Sharat Batra, PhD·6 min read

A PDF sits in a folder. A structured web page creates nodes in a knowledge graph, feeds an AI assistant, and gets richer every time new content connects to it. The container you choose determines whether wisdom accumulates or stagnates.

Read the full post

From Textbook to Narrated Video in One Session

April 15, 2026·Arun Batchu & Claude (AI)·4 min read

We generated a complete intelligent textbook, a 30-slide lecture deck, and a narrated video lecture — all in a single Claude Code session. The real lesson is not the speed. It is the pipeline.

Read the full post

The blog is only the surface

The dispatches capture the thinking. The research briefs, experts, and working systems are where it compounds.