Skip to content
aiaz·labs

AI engineering lab · actively developed

Engineeringthenextgenerationofintelligentproducts.

A working lab for AI interfaces, retrieval (RAG), accessibility and performance. Every project is built, tested and shown running, so you can judge it for yourself.

Explore projectsRead the research

12 projects · 4 disciplines

Projects

Four disciplines. One lab.

Choose a project to preview it, then open its full write-up.

  • 4 in progress
  • 8 planned

  • AI Interfaces

    Interfaces for intelligent systems

    • StreamingChat preview
      AI InterfacesIn progress

      StreamingChat

      View project StreamingChat

      Token-by-token chat UI with markdown rendering, abort, retry and optimistic message state.

      • SSE
      • Markdown
      • React 19

  • RAG

    Retrieval you can trust

  • Accessibility

    Inclusive by construction

  • Optimised

    Fast at scale

Labs · research

Notes, experiments and findings from building these projects

All research
  • AI Interfaces4 min read

    Building a streaming chat UI that doesn't jank

    Token-by-token rendering, scroll behaviour and abort handling — the patterns that keep an LLM chat feeling instant.

    • Streaming
    • React 19
    • UX
    Read the note
  • RAG6 min readComing soon

    Citations users can actually verify

    How to ground RAG answers and link every claim back to the exact source passage.

    • RAG
    • Grounding
    • Citations
    In the works
  • Accessibility7 min readComing soon

    Keyboard-first comboboxes: ARIA 1.2 in practice

    What the spec says, what screen readers really announce, and the bugs that slip through.

    • ARIA
    • Keyboard
    • WCAG 2.2
    In the works