berk.ai

Toolbox

My Toolbox

Over the years, I’ve refined a development workflow centered around a carefully selected set of tools, platforms, and technologies. My goal isn’t to chase every new framework—it’s to assemble a toolbox that lets me move quickly from an idea to a production-ready product while maintaining quality, reliability, and a great developer experience.

I constantly evaluate new technologies, but only adopt them when they meaningfully improve the way I build software. The result is a modern, AI-first engineering workflow that allows me to prototype in hours, iterate in days, and ship production systems with confidence.

Rather than viewing AI as a feature, I treat it as an integral part of my engineering process—from architecture and implementation to testing, documentation, deployment, and ongoing maintenance.

AI Development

These are the tools I work with throughout the day to accelerate development, explore ideas, generate code, review designs, and solve complex technical problems.

  • Cursor
  • ChatGPT
  • OpenAI Platform
  • Codex
  • Claude Code
  • OpenClaw
  • LM Studio
  • Ollama
  • Jupyter Notebooks

Application Platform

My preferred stack for building modern SaaS products and AI applications.

  • Next.js
  • React
  • TypeScript
  • Kotlin
  • Ruby
  • Ruby on Rails
  • AI SDK
  • Drizzle ORM
  • Better Auth
  • Postgres
  • Redis
  • Tailwind CSS
  • Radix
  • shadcn/ui
  • Node.js

Cloud & Infrastructure

Infrastructure designed to make deployment, scaling, and operations simple.

  • Vercel
  • Fly.io
  • AWS
  • Google Cloud Platform
  • Kubernetes
  • GitHub
  • Neon
  • Cloud Object Storage
  • Docker

Product Operations

The tools I rely on to monitor, improve, and operate production systems.

  • Datadog
  • PostHog
  • Linear
  • Resend

Local Development

A productive local environment is essential for rapid experimentation and iteration.

  • Tailscale
  • Ollama
  • LM Studio
  • Docker
  • Git
  • macOS
  • Homebrew

Engineering Philosophy

My toolbox is intentionally opinionated.

I prefer technologies that are simple, composable, and well documented. I value developer experience just as highly as runtime performance, because great products are built by teams that can iterate quickly.

When evaluating new tools, I look for:

  • Excellent developer experience
  • Strong type safety
  • First-class AI integration
  • Production reliability
  • Fast local development
  • Clear documentation
  • Vibrant communities
  • Minimal operational complexity

The specific tools in my toolbox will continue to evolve, but the philosophy remains the same: choose technologies that remove friction, encourage experimentation, and allow great ideas to become working software as quickly as possible.