Engineering leader who writes about what actually works.

I build software, lead teams, and write about the gap between what technologies promise and what they deliver.

Prem Chandrasekaran
Published AI-Augmented SDLC: Part 3 - Making It Work Apr 29 Pushed to GitHub 1w ago Updated /now 4w ago

Latest Writing

View all →
AI-Augmented SDLC: Part 3 - Making It Work

AI-Augmented SDLC: Part 3 - Making It Work

AI tools accelerate delivery when BOTH conditions hold: pre-coding is settled and post-coding is representable in the coding process. Here's the formula — and what to fix if you want to actually ship faster.

AI-Augmented SDLC: Part 2 - The Bottlenecks

AI-Augmented SDLC: Part 2 - The Bottlenecks

AI tools compressed coding time. But requirements, architecture, cross-team dependencies, and post-coding friction didn't compress with it. Faster coding meant faster arrival at the next blocker.

AI-Augmented SDLC: Part 1 - The Ecosystem

AI-Augmented SDLC: Part 1 - The Ecosystem

AI coding tools represent a genuine step change. Skills encode domain expertise, subagents handle scale, MCP integrations keep you in flow. Here's what the ecosystem can actually do — across three real projects.

Recent Talks

View all →
Arc of AI

AI-Assisted Development: What Actually Works

Lessons from three real projects on where AI coding tools accelerate delivery — and where they just accelerate rework.

2026
Neo4J Nodes AI

Graph-Powered Storyworlds

Using Neo4j to keep 1M+ word LitRPG epics coherent with AI — knowledge graphs as narrative immune systems.

2026