Chatterbrain

Inspiration

Many autistic individuals, like myself, want to improve their social skills but lack a supportive, pressure-free environment to practice. Traditional social skills training often feels clinical, judgmental, or one-size-fits-all. I was inspired to build Chatterbrain to give neurodiverse users a voice—literally—by offering a gamified, affirming, and deeply personal way to build communication skills and social confidence.

What it does

Chatterbrain is an interactive web platform that helps autistic users practice social interactions through dynamic, scenario-based dialogues. Users are guided through realistic conversations with multiple response options. They receive feedback based on five core communication traits—clarity, empathy, engagement, social awareness, and self-advocacy—and can track their growth, earn achievements, and progress through levels. Voice narration makes the experience immersive and accessible.

How We Built It

Frontend: Built with TypeScript and React, styled using SCSS. Zustand handles state management for a smooth, reactive experience.
Backend: Supabase (PostgreSQL + Auth) manages user accounts, dialogue content, and scoring logic with real-time updates.
Integrations & AI: ElevenLabs powers realistic voice previews, while OpenAI drives dialogue generation and user feedback. Bolt.new played a crucial role in speeding up UI development, handling API integration, and refining the user experience through guided assistance.
Design: A clean, intuitive interface with soft visuals and calming UX was designed to support neurodivergent users in a low-pressure environment.

Challenges we ran into

Learning Supabase on the fly, especially with row-level security and database relationships.
Communicating clearly with Bolt.new to get results closely aligned with design and functionality goals.
Designing a scoring system that feels both meaningful and affirming, without being judgmental.
Managing GitHub workflow while using the Bolt editor in parallel introduced occasional version control friction.

Accomplishments that we're proud of

Built a complete, interactive learning platform tailored for autistic users.
Crafted a user interface that balances calm, simplicity, and accessibility.
Successfully integrated realistic voice narration using ElevenLabs.
Developed a recommendation system that adapts to each user’s goals and interests.

What we learned
Gained hands-on experience with Supabase, OpenAI, ElevenLabs, Zustand, and SCSS.
Learned how to prompt and collaborate with Bolt.new effectively—using discussion mode, enhanced prompts, and clear role-based instructions.

What's next for Chatterbrain

Multiplayer Mode: Simulated group dialogues for more dynamic practice.
Scenario Builder: Empower coaches, therapists, or teachers to create custom practice flows.
AI-Powered Feedback: Offer deeper insights into tone, timing, and social cues.
Community Support: Incorporate tips and feedback from real coaches and fellow users to provide encouragement, guidance, and actionable insights for improvement.
Smarter Progress Tracking: Refine the scoring system to better reflect user growth. The goal is to give users a clear sense of where they stand, what they’ve achieved, and what specific steps they can take to improve.
Booster Tools: Add features like a rephrasing, tone detector, or social cue identifier for more in-depth learning support.