Blog
Technical writing on backend systems, architecture decisions, and engineering trade-offs.
LLM Headroom: Slashing Token Consumption by 60–95% in Agentic Workflows
AI agents running inside tools and loops are incredibly resource-intensive. Learn how chopratejas/headroom uses reversible compression and AST-aware tools to optimize LLM contexts and slash token costs.
The Great Token Migration: Is GitHub Copilot Pricing Out Indie Developers?
GitHub Copilot's shift from flat subscriptions to metered token-based billing is leaving individual devs behind. Explore the cost comparison, workflow profiles, and open alternatives like DeepSeek V4, OpenCode Go, and Cursor.
The Edge-Native Web: Deep Dive into Astro's Island Architecture & Cloudflare Workers
Dissecting the internals of Astro's partial hydration, Cloudflare's V8 Isolate architecture, and the mechanics of sub-50ms global latency.
The KMP Renaissance: Under the Hood of Kotlin Multiplatform and the K2 Compiler
An architectural breakdown of Kotlin Multiplatform's backend, exploring the K2 compiler, the new Memory Model, and Skia-based rendering in Compose.
Engineering in the Age of Agents: Orchestrating LLM Workflows
A deep dive into transitioning from deterministic pipelines to non-deterministic, agentic multi-node architectures using ReAct, DAGs, and Context Injection.