AWS Hackathon · Runner-up · Live Event System
HIVEMIND
turning a whole event into one collective thought
Built at an in-person AWS hackathon. Every attendee sends a single word from their phone. We funnel those words into a central brain that periodically generates a single sentence describing what the whole crowd is thinking.
Lambda writes each word into Couchbase. Another Lambda samples a random subset, feeds it to Amazon Bedrock, and renders the resulting “hive thought” on the main event screen.
Live event brain
Everyone sends one word. The screen shows one mind.
Inputs from hundreds of attendees are sampled, remixed via Bedrock, and surfaced as a single animated thought on the main display.
Sample hive output
“We're a room full of builders, running on caffeine, hoping the demo gods are kind.”
The Concept
Many words. One thought.
placeholder
Powered by Amazon Bedrock
How it works
from word input to crowd thought
1. One-word input
Each attendee submits a single word from a simple web form on their phone.
2. Lambda → Couchbase
An AWS Lambda function writes the word, user/session metadata, and timestamp into Couchbase.
3. Sampling the hive
A scheduled Lambda grabs a random subset of recent words to avoid the same few people dominating.
4. Prompting Bedrock
Words become a compact prompt — Amazon Bedrock generates a single "hive thought" for the room.
5. Main-screen render
The thought is pushed to the event display as a glowing banner, updating as more people submit.
Team
Built by a two-person team focused on live systems and crowd interaction.
