Writings and Learnings

Essays on AI agents, full-stack systems, and building in public.

2026-06-08
the_y_coding_standard: I Encoded My Entire Engineering Brain Into a Claude Code Plugin

A deep dive into how I built an open-source Claude Code plugin that makes AI agents write code exactly the way I would - silently, consistently, across every project and every session.

AI EngineeringClaude CodeOpen SourceDeveloper ToolsAgentic AISoftware Architecture
2026-05-30
Doxa: The Memory Indian Doctors Never Had

Why I'm building Doxa, an AI medical memory layer for India's 800,000 paper-based clinics, where doctors see 40 patients a day and remember none of them after they walk out.

healthcareaistartupsindiaambient-ai
2026-05-29
y-brain: How I Turned Claude Code Into a One-Person Engineering Team

I stitched together 130+ skills from Anthropic, Vercel, GStack, and Matt Pocock into a single Claude Code environment that auto-commits itself, here's why it matters.

claude-codeai-engineeringdeveloper-toolssecond-brainproductivity
2026-05-28
Notes from after Binocs

A year onsite at a Bangalore startup teaches you a few things. These are mine, and what I've been building since I left.

binocsstartup-lifeclaude-codebuilderdoxa
2026-05-23
Beyond pass@1: A Reliability Science Framework for AI

Transitioning from simple performance metrics to a robust Reliability Science framework for evaluating long-horizon LLM agents.

arxivllmbenchmarkingreliability
2026-05-23
Effective Context Engineering for AI Agents

Context Engineering is the art of curating the optimal set of tokens to maximize an agent's attention budget.

anthropiccontextllmprompt-engineering
2026-05-23
Effective Harnesses for Long-Running Agents

Overcoming the Long-Running Agent Problem with a Two-Fold System and structured state management.

anthropicagentslong-runningllm
2026-05-23
GitHub Spec-Kit: Executable Blueprints for SDD

Spec-Driven Development turns documentation into executable blueprints for AI agents.

spec-kitgithubSDDai-agents
2026-05-20
NRQL Predictions: Forecasting Future Trends in New Relic

How NRQL predictions use Holt-Winters exponential smoothing to forecast time series metrics.

observabilityNRQLMLforecasting
2026-05-15
How I Reduced Claude API Cost by 99% with Prompt Chaining

From $1.00 to $0.01 per slide — redesigning an AI presentation pipeline with structured outputs and prompt chaining.

AILLMClaudeoptimizationprompt-engineering
2026-05-10
Building Real-Time Systems: WebSockets, Redis, and Sub-50ms Latency

Architecture decisions behind a real-time chess platform with sub-50ms move propagation and ELO matchmaking.

websocketsredisreal-timesystemstypescript