Theo Browne

Theo distinguishes product breadth7 from feature depth and describes how extension points, interfaces for adding features, let users build missing features. AI Engineer World’s Fair, 13:23 14:37.

He argues that a model’s ordinary reliability matters more than its best result when agents work on longer tasks. Please stop using stupid models, 04:19.

Sources

  1. Everything we knew about software has changed — Theo Browne, @t3dotgg ​ - YouTube. Theo Browne. World's Fair talk; used for wider software work and extensible products. Accessed 2026-10-01.
  2. Please stop using stupid models - YouTube. Theo Browne. Model discussion; used for the reliability floor on long agent runs. Accessed 2026-10-01.
  3. It's Time To Rethink Everything by @t3dotgg - YouTube. Theo Browne. CascadiaJS talk; used for rethinking assumptions and building bigger. Accessed 2026-10-01.

Last changed 2026-10-07 in f1a00f2. Source on GitHub. Change log.

Linked from

  1. Agent guide. An Effect stack so pure (aspirational) Kit Langton will blush.

    Theo Browne — Theo Browne discusses broader software work and model reliability in public talks.

  2. Change log. What changed in the files served here, newest first.

    Theo Browne — edited: feat(learn): teach cards 63 to 82 with plain lines, diagrams and snippets

  3. Full agent guide. An Effect stack so pure (aspirational) Kit Langton will blush.
  4. Rat Stack lore | rat-stack. Short, source-grounded notes on the ideas and decisions behind rat-stack.

    Theo Browne — Theo Browne discusses broader software work and model reliability in public talks.

  5. Source change history (log.md). The generated change log as Markdown.

    Theo Browne — edited: feat(learn): teach cards 63 to 82 with plain lines, diagrams and snippets

  6. Think wider. Theo Browne asks developers to cover more product breadth instead of adding depth in one narrow area.

    See AI Engineer World’s Fair 2026 and Theo Browne.¶