Gareth Austen AI systems · product engineering

Notes from the workbench

I build AI systems that have to work in the real world.

I’m Gareth Austen, a software and machine-learning engineer in Dublin. This is where I write about optimising Agents, developing robust quality gates, designing good evals, building Tell Me Ted, working with coding agents, and turning prototypes into dependable products.

Latest writing

All writing

  1. From Chained AI Calls to a Realtime Voice Experience

    Why a sequence of individually sensible AI calls created the wrong conversational rhythm and why we moved toward a more continuous voice experience.

    Building Tell Me Ted· Artificial Intelligence· Voice AI

  2. What’s Inside an AI Teddy Bear?

    A high-level tour of the sensing, processing, connectivity, audio and power systems behind an AI-enabled reading companion.

    Building Tell Me Ted· Voice AI· Embedded Systems

  3. Codex Can Write the Code. You Still Own the System.

    Codex accelerated a major refactor, but a lifecycle-critical capability needed follow-on repair. Here is how we improved our tasks, tests and review process.

    Building Tell Me Ted· Codex· Embedded Systems

Series in progress

Building Tell Me Ted

Twelve field notes on building a physical AI product: the architecture, the hardware, the judgement calls and the mistakes.

  1. 01 We’re Building a Teddy Bear That Can Read With a Child
  2. 02 Building a Startup With ChatGPT as a Daily Collaborator
  3. 03 Codex Can Write the Code. You Still Own the System.
  4. 04 What’s Inside an AI Teddy Bear?
  5. 05 From Chained AI Calls to a Realtime Voice Experience
View the complete series