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. 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

  2. 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

  3. Building an AI Hardware Product With ChatGPT as a Daily Collaborator

    A practical account of how a small team uses ChatGPT across product thinking, software, hardware and decision-making—and where human judgement remains essential.

    Building Tell Me Ted· Artificial Intelligence· Codex