Signal Words
Turns spoken instructions into a visual sequence for a user who processes images faster than speech. Built for Say It Back — build a voice interface for someone who cannot comfortably use a screen. Speech-to-storyboard pipeline. The interface is deliberately narrow: one path, done properly, rather than a broad surface that half-works at the deadline.
Gallery
Screens
Signal Words — main view
Signal Words — result state
On the clock
What shipped, what didn't
Completed in time
Speech-to-storyboard pipeline.
Unfinished / faked
Image generation adds four seconds of latency.
Obstacles
A dependency version mismatch cost six minutes. Pinned it and moved on.
Lessons learned
Boring, well-understood tools beat interesting ones when there's no time to debug.
Process
Prompting approach
Started from a single system prompt describing the user and their constraint, then iterated with the assistant on the Signal Words 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.
Started from the official framework starter template, unmodified.
Judging
Public feedback
Judges' private notes stay private — this is what they chose to say publicly.
Hana Kobayashi
Principal Research Engineer, Independent
The AI component feels bolted on. Ask yourself whether the product still works if you removed the model — here, I think it does.
Ravi Anand
Head of Design, Tessellate
Ambitious in a way that worked against you. Half of a large idea scores lower than all of a small one.
Tomas Eriksen
Developer Advocate, Independent
Ambitious in a way that worked against you. Half of a large idea scores lower than all of a small one.
Discussion
0 comments
No comments yet.