WORK / RESEARCH FOCUS

John Brown builds real-time conversational AI, on-device voice systems, and agent tooling.

I work on the timing and dynamics of spoken interaction: when a system should speak, listen, backchannel, or hold back. The same practice spans ML evaluation, Swift/CoreML deployment, AI-agent orchestration, and technical direction for work that has to move from research to operated systems.

JB// VOICE TIMING JB// ON-DEVICE ML JB// AGENT TOOLS JB// SOUND ARCHIVE JB// IMAGE STUDIES JB// TECHNICAL DIRECTION JB// VOICE TIMING JB// ON-DEVICE ML JB// AGENT TOOLS JB// SOUND ARCHIVE JB// IMAGE STUDIES JB// TECHNICAL DIRECTION

WORKING THREAD

From ear to system

John Brown works where timing becomes software behavior: audio timing, real-time voice AI, on-device systems, and the engineering habits needed to ship and maintain them.

The site collects technical notes, sound sketches, and visual studies without pretending they are the same kind of artifact. They share a concern with timing, control, and readable systems.

  1. 01

    Listen for timing

    Audio, guitar, synthesis, and production keep the work grounded in latency, groove, texture, and restraint. This is where the ear for timing becomes an engineering constraint.

  2. 02

    Model interaction

    Those timing instincts become conversational policy: turn-taking, backchannels, VAD projection, affect signals, and evaluation tied to what the system should actually do.

  3. 03

    Ship under frame pressure

    Research has to survive on-device budgets, Swift/CoreML deployment, streaming state, fixed hop sizes, and pre-allocated audio loops.

  4. 04

    Leave a readable record

    ADRs, release gates, notes, images, sound sketches, and repos make the work inspectable so another person can pick it up cold.

WORK / RESEARCH

Current focus map

The technical center is real-time, on-device interaction. Music stays close because timing, tools, and constraints show up there too; image work can stay quiet until there is a fuller public set.

  • Real-time conversational AI

    Turn-taking, backchannel behavior, VAD projection, and affect-aware policy for systems that know when to speak, listen, or hold back.

  • On-device voice systems

    Hard real-time streaming paths with causal models, bounded state, fixed hop budgets, and clear fallbacks under frame pressure.

  • AI-agent tooling & orchestration

    Protocol servers, model-provider abstractions, agent gateways, lifecycle tooling, and wave-structured multi-agent delivery.

  • Technical direction

    ADRs, staged releases, roadmaps, acceptance gates, and interface contracts that keep research-to-deployment work operable.

FEATURED ENTRY POINTS

Recent work and notes

Start with technical notes, then scan music entries for the same timing and systems concerns in another medium.

  • Real-time conversational AI for voice systems

    Design notes for on-device voice systems with explicit turn-taking, listener behavior, and affect-aware conversational policy.

    • notes
    • conversational-ai
    • voice
    • real-time-systems
    OPEN ENTRY
    • PUB 2026-06-02
    • CAT notes
    • STATE PUBLISHED
    • TAGS 04
  • SoundCloud sketch archive

    A public index of SoundCloud sketches, modular patches, and track fragments under the johnthomas profile.

    • music
    • soundcloud
    • sketches
    • modular
    OPEN ENTRY
    • PUB 2026-06-01
    • CAT music
    • STATE PUBLISHED
    • TAGS 04
  • AI agent tooling and wave-based orchestration

    A practical direction for agentic systems: protocol-first tooling, multi-provider abstractions, and staged delivery with interface contracts.

    • notes
    • ai-agents
    • orchestration
    • protocol
    OPEN ENTRY
    • PUB 2026-06-01
    • CAT notes
    • STATE PUBLISHED
    • TAGS 04
  • Static publishing stack for a personal site

    Notes on using Astro, structured content, GitHub Actions, and SSH deployment as a small personal publishing system.

    • notes
    • astro
    • github-actions
    • publishing
    OPEN ENTRY
    • PUB 2026-06-01
    • CAT notes
    • STATE PUBLISHED
    • TAGS 04

SECTION MAP

Where to go next

Start with the routes that have enough public material right now: notes and music.

PLATFORMS / CONTACT

Available channels

One compact surface for collaboration, technical context, sound sketches, and public work.

Preferred contact surface

For collaboration, project alignment, and technical direction requests, lead with GitHub or LinkedIn notes and include timeline, scope, and constraints.

Project work
GitHub for repo context, issue-shaped notes, and implementation threads.
Professional context
LinkedIn for introductions, interviews, and role-shaped conversations.
Creative process
SoundCloud, Instagram, and Threads carry sound sketches and visual process.