[SYS.USES]
Uses.
Tools, languages, and services I use to build things.
This is the current stack I reach for to build AI-native software: the editors, AI models, languages, frameworks, cloud services, and hardware I actually use day to day. Last reviewed .
[EDITOR & IDE]
My primary coding tool. Agentic CLI that lives in the terminal. I use it for everything from scaffolding to debugging to git workflows.
VS Code fork with AI built in. I use it when I need a visual editor alongside Claude Code, especially for frontend work.
OpenAI's agentic coding CLI. I keep it in rotation to compare approaches and use it for tasks where GPT-5-CODEX shines.
Runs a fleet of Claude Code agents across isolated git worktrees so I can parallelize work instead of babysitting one terminal. It's how I actually get through a backlog: fan out, review, merge.
Voice dictation that actually keeps up with me. I talk out prompts and commit messages instead of typing them, and it cleans up the ums and false starts automatically. Way faster than the keyboard for long-form input.
[LANGUAGES]
My default for everything web. Full-stack with Next.js, API routes, AI SDK integrations, strict mode always on.
For ML pipelines, scripting, and tools like DreamPixel Forge. Also the backbone of most MCP server prototyping.
[FRAMEWORKS & LIBRARIES]
App Router, server components, API routes. My go-to for every web project. This site runs on Next.js 16.
React 19 with server components. I prefer composition over complexity: context for state, RSC for data.
Utility-first CSS. Custom design tokens for every project, no component libraries. Tailwind v4 on this site.
Unified interface for streaming LLM responses, tool calling, and structured output. Powers the terminal chat on this site.
[SERVICES & INFRASTRUCTURE]
Auth, Firestore, and hosting for most of my SaaS projects. Fast to ship, scales well enough for the 0-to-1 phase.
Deploy target for all Next.js projects. Preview deployments and edge functions make iteration fast.
API for running open-source ML models. I use Flux Schnell for image generation in several projects.
[AI & LLMS]
My main LLM for coding, writing, and thinking. Opus for hard problems, Sonnet for speed. Claude Code is my daily driver.
GPT-5 powers the chat on this site. I also use the embeddings API for RAG pipelines.
Google's model. I use it in MCP servers for multimodal tasks like YouTube video analysis and image generation.
[HARDWARE]
My main machine. The 14-inch is the sweet spot: enough screen to work, still light enough to throw in a bag. Apple Silicon runs local models and heavy builds without the fans ever really spinning up.
Split ergonomic keyboard. The two halves let my shoulders sit where they want instead of squared up to a slab. If you type all day and your wrists hurt, this is the fix. Takes about a week to stop fumbling the split.
Vertical mouse that keeps your hand in a handshake position instead of pronated flat. Pairs with the Kinesis for a fully neutral desk. Feels weird for a day, then you can't go back to a normal mouse.
My phone. Big screen, the S Pen is genuinely useful for quick notes, and the camera holds up against anything. I stay on Android for the openness, and the Ultra is the one that doesn't compromise.
Rugged smartwatch with battery life measured in weeks, not hours. I wear it because I don't want to charge a watch every night like an Apple Watch. GPS and health tracking are solid, and it survives being knocked around.
Some hardware links are Amazon affiliate links. As an Amazon Associate I earn from qualifying purchases, at no extra cost to you.