Skip to main content
codingstairs

AI, apps, and architecture

Choose AI, app, and architecture techniques with execution limits and cost in mind.

By the end of this path

Compare purpose and cost, then design replaceable boundaries for AI, app, and architecture choices.

Before you start

Knowing basic API, data, and deployment concepts will make the trade-offs easier to compare.

Learning sequence

  1. 1

    AI-native developer tooling — Claude Code · MCP · design tools

    Beginner

    A 7-step path to using AI tools beyond chat — MCP, Skills, Subagents, workflows, and design-side tooling.

    7 stepsStart →
  2. 2

    Local LLM · pgvector · building a RAG chatbot

    Advanced

    Connect LM Studio, pgvector, Gemini, and browser ONNX inference in eight steps, from retrieval to model-delivery cost.

    8 stepsStart →
  3. 3

    Tauri 2 — desktop · mobile in one codebase

    Intermediate

    Ship desktop and Android apps from a single Rust + web frontend. Seven steps — IPC to OCR to AdMob.

    7 stepsStart →
  4. 4

    Monorepo · SSOT · layer separation thinking

    Advanced

    Six mental steps to running several services from one repository.

    6 stepsStart →
Start with AI-native developer tooling — Claude Code · MCP · design tools →