Build: guides and tools for shipping software with AI

Step-by-step guides for shipping with AI.

A developer typing at a keyboard in a dim room, lit by two out-of-focus monitors.
Photo by cottonbro studio on Pexels

Latest in Build

26 stories

  1. Prompt caching explained: how to cut your AI API bill without changing models

    Derrick K.

  2. Run OpenCode on a local model: Ollama, LM Studio and llama.cpp configs that work

    Derrick K.

  3. Ollama for beginners: run your first local AI model in 5 minutes

    Derrick K.

  4. LLM API pricing compared: Claude, Gemini, GPT-6, MiniMax and Mercury, side by side (Oct 2026)

    Derrick K.

  5. gemini-api CLI: give Claude Code or Codex image, voice and video generation in 5 minutes

    Derrick K.

  6. DESIGN.md: give your coding agent a design system so every page looks the same

    Derrick K.

  7. Context windows explained: tokens, 1M-token models and what actually fits

    Derrick K.

  8. Codex CLI from zero: install, sign in, /init and your first task

    Derrick K.

  9. Claude Opus 5.5 for builders: price, 1M context, and the four changes that break Opus 5 code

    John F.

  10. Claude Code subagents vs skills vs hooks: which one to use, with examples

    Derrick K.

Codema Daily

A short daily note on AI, building, hardware and AI money.

Nothing is saved yet. Email delivery is not connected, so this form does not store your address.