Flowra · Conversation coaching

A conversation.
A chance to grow.

A team desktop prototype for reflecting on conversations, practicing responses and receiving live assistance.

01 · Listen

Begin with
what was said.

Separate microphone and system-audio capture paths support transcription and a conversation timeline.

02 · Reflect

Make room
for reflection.

Transcript review and analysis help structure the next step. Gemini through OpenRouter supports the prototype’s AI flows.

03 · Practice

Try a response.
Try another.

Practice and live-assistance views connect the conversation to feedback. The interface shown here is an explanatory concept.

04 · Recognition

Built to be useful.

Flowra received the Most Useful award at the Socia Global Build Challenge. Co-developed with Majd Alddin Sukkary.

Three-dimensional Flowra interface concept showing conversation reflection, practice and a synthetic audio waveform.
FLOWRAIllustrative interface concept · synthetic example text
Read the case study
Scroll or use arrow keys on the slider

Team desktop prototype · March 2026

Flowra

A place to reflect on conversations and practice what comes next.

ElectronReactTypeScriptGeminiSupabase

01 / Purpose

What we set out to do.

Help a person review a conversation, practice responses, and receive assistance while speaking.

02 / Approach

How it came together.

Electron, React, and TypeScript provide the desktop application. Gemini through OpenRouter supports analysis, practice, transcription, and live advice. Supabase stores application history. Microphone and system audio follow separate capture paths.

03 / Contribution

The work, and the team.

Co-developed by Husain Altelly and Majd Alddin Sukkary. Repository history establishes involvement but does not justify assigning every feature to one teammate.

04 / Demonstration

What the visuals show.

The inspected source includes transcript review, practice, and live-assistance flows. Labels distinguishing microphone and system audio should not be described as general multi-speaker diarization.

05 / Results

What we can say.

Flowra received the Most Useful track award at the Socia Global Build Challenge, corroborated by the organizer's announcement.

06 / Limitations

Where the limits are.

This review did not independently test live provider behavior, transcription accuracy, latency, or real-user outcomes. The project is a prototype, not a clinically validated coaching tool.

07 / Lessons learned

What I’m taking forward.

Audio capture, useful feedback, and clear interface states all matter when designing an application around a live conversation.

Next project

AURORA Mission X

Visual sources & attribution

Blender visuals explain the projects. Balancing-robot geometry, the planning environment, Flowra interface and AURORA lander are original illustrative concepts made for this portfolio. Their movement, example text and layouts are not recorded results, original course CAD, production screenshots or gameplay.

The T42 scene uses Yale OpenHand Model T42 CAD from the OpenHand repository, licensed CC BY-NC 3.0. The assembly, materials, actuator housings, tendon path and deformation are illustrative. Cast contact materials are not reconstructed.

R. R. Ma, L. U. Odhner, A. M. Dollar, “A Modular, Open-Source 3D Printed Underactuated Hand,” ICRA 2013.

The Yale OpenHand Project is an initiative to advance the design and use of robotic hands designed and built through rapid-prototyping techniques in order to encourage more variation and innovation in mechanical hardware. Please visit the Yale OpenHand site for more details.