Skip to content
Live nowSeason 1 ยท Episode 5 ยท GPS
AI

Campfire

A live audience-reaction layer for technical talks, built to be readable from the back of a room. Built for Cabin Build โ€” first team challenge. three builders, one repository, 30 minutes. Realtime reaction stream and the projector view. The interface is deliberately narrow: one path, done properly, rather than a broad surface that half-works at the deadline.

Emberline CabinSubmitted โ€”49.8/ 100
๐Ÿ”ฅ 36๐Ÿš€ 10๐Ÿคฏ 3

Gallery

Screens

Campfire โ€” main view

Campfire โ€” result state

On the clock

What shipped, what didn't

Completed in time

Realtime reaction stream and the projector view.

Unfinished / faked

Untested above ~200 concurrent viewers.

Obstacles

Underestimated the parsing work. Cut a whole feature to protect the demo.

Lessons learned

Scope down before the timer starts, not at minute 20 when you're already committed.

Process

Prompting approach

Started from a single system prompt describing the user and their constraint, then iterated with the assistant on the Campfire 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.

Pre-existing code reusedNone
Template or boilerplate usedDisclosed

Started from the official framework starter template, unmodified.

CollaboratorsTheo Lindqvist, June Park, Luz Herrera
Work before the build windowNone

Judging

Public feedback

Judges' private notes stay private โ€” this is what they chose to say publicly.

Elena Voss

VP of Engineering, Harbor Compute

Nice work under the clock. The unfinished list is longer than the finished one, but what shipped works and you were straight about it.

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.

Claudia Reyes

Staff Engineer, Vantage Analytics

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.

Campfire ยท ๐Ÿ•๏ธ AI