back to projects

Minute Maker

featured

AI tool built with Cal Poly DxHub and Lynwood Unified School District that turns board meeting recordings into accurately cited minutes, cutting a 24-hour manual process down to under an hour.

AWS BedrockStep FunctionsLambdaNext.jsTypeScriptPython

School districts and local agencies were spending up to 24 hours per meeting manually transcribing and formatting board minutes, at roughly $24/hour. Minute Maker processes the meeting recording and agenda together and produces cited, ready-to-publish minutes for a fraction of the cost and time, so meeting outcomes reach the public faster.

Built with Gus Flusser on a serverless AWS stack: Bedrock for the language model work, Step Functions and Lambda for orchestration, API Gateway, S3, and Cognito for auth, with a Next.js/TypeScript frontend and Python on the backend.