Stop Engineering Your Prompts and Just Talk to the Thing
Most developers overcomplicate their AI coding workflow with elaborate setups and prompt rituals. The agents are good now. The bottleneck is you.
Writing & thoughts
AI Is the Best and Worst Thing to Happen to Junior Engineers
Junior engineers ship faster than any generation before them. They also skip the struggle that builds intuition. That tradeoff is going to cost us.
Self-Hosting n8n, Supabase, and My Entire Automation Stack on a Hetzner VPS
A walkthrough of how I provisioned a Hetzner VPS with Terraform, deployed Dokploy, and self-hosted my entire automation infrastructure for the cost of a coffee per month.
Building LLM APIs in 2025: What Nobody Tells You
The unglamorous realities of building production APIs around Large Language Models. Latency, cost, context windows, and why streaming isn't optional.
I Automated My Social Media Content Pipeline with n8n and LLMs
How I built a workflow that fetches news, generates social media posts with an LLM, and schedules them automatically. My content robot works harder than I do.
n8n vs Make.com vs Zapier: I Tried All Three So You Don't Have To
An honest comparison of the major automation platforms in 2025. Spoiler: I ended up self-hosting n8n.
Geospatial queries with mongoose and TypeScript
Avoiding Harvesine formula when calculating the distance between two points with mongoose's <code>$geometry</code> and <code>$maxDistance</code> operators.
Processing large datasets in chunks with Node.js
How to use the readline module in order to process large datasets in chunks and thus not blocking the main thread.
Enter React Server Components
An introduction to what React server components are and how this broadens React use cases.