Say The Word
The single field is a microphone. Speak a task, get a result. Built for One Prompt — ship a useful product where the entire interface is a single prompt field. Voice-to-action with confirmation. The interface is deliberately narrow: one path, done properly, rather than a broad surface that half-works at the deadline.
Gallery
Screens
Say The Word — main view
Say The Word — result state
On the clock
What shipped, what didn't
Completed in time
Voice-to-action with confirmation.
Unfinished / faked
Only four verbs supported.
Obstacles
The first approach needed a background worker I didn't have time to deploy, so I moved it inline at minute 14.
Lessons learned
The demo path is the product. Everything not on it can wait for next time.
Process
Prompting approach
Started from a single system prompt describing the user and their constraint, then iterated with the assistant on the Say The Word data model before writing any interface code. Full prompt log is in the repository under /prompts.
Fairness
Disclosures
Declared by the builder at submission time, visible to judges before scoring.
Judging
Public feedback
Judges' private notes stay private — this is what they chose to say publicly.
Marcus Bell
Founder, Bellwether Studio
Good instinct on the problem. I would have liked to see the model doing more of the reasoning rather than formatting output.
Hana Kobayashi
Principal Research Engineer, Independent
The idea is strong and the execution is most of the way there. The demo path broke once, which is what separates this from the top three today.
Ravi Anand
Head of Design, Tessellate
Good instinct on the problem. I would have liked to see the model doing more of the reasoning rather than formatting output.
Discussion
0 comments
No comments yet.