BinBrain — recycling sorting on Ring

Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

What we learned

What's next for BinBrain — recycling sorting on Ring

Inspiration

For urban households, contamination rates are high because the rules differ by council. We wanted something that just handled it instead of adding another dashboard. Ring was the obvious place to put it because event triggered by the doorbell is already how this audience works.

What it does

At its core BinBrain is sorting household waste correctly. Around that it adds memory (so history actually changes the next decision), a scheduler (so it happens without being asked), and a thin event triggered by the doorbell layer so the interaction feels native to the doorbell and cameras.

How we built it

The agent is written in Python with boto3 and runs on AWS Lambda, calling Amazon Comprehend for the reasoning steps. State lives in S3 + Athena, Kinesis and Glue glue the scheduled and event paths together, and the whole stack deploys from a single CDK/CloudFormation app.

Challenges we ran into

Latency, mostly. Anything reached through the doorbell and cameras is judged in the first second, so we spent more time on warm paths and caching than on the model itself. The other half was evaluation: with recycling sorting there is no single right answer, so we had to define a scoring rubric before we could tell whether a change helped.

Accomplishments that we're proud of

It works unattended. We left it running for a week and it kept producing useful output without anyone touching it — that was the moment it stopped being a demo. It also costs almost nothing to run, which matters for urban households.

What we learned

boto3 makes it easy to attach real state to an agent; the hard engineering is conflict resolution between tools once they disagree. We also learned how much of perceived quality in a Ring experience comes down to latency rather than model choice.

What's next for BinBrain

Next we want shared use so two people can edit the same plan, a cost estimate driven by live pricing, and a second surface — moving from the doorbell and cameras to a companion view so the same agent is usable in more than one room.

Built With

• amazon-comprehend
• amazon-ring
• aws-lambda
• binbrain
• boto3
• waste