Inspiration
We were inspired by how powerful AI can become when agents collaborate rather than work in isolation. The idea of turning multiple specialized agents into a single, smooth workflow sparked the concept for Synkron.
What it does
Synkron takes uploaded user data and runs it through six AI agents — each performing a unique step from data exploration to insight generation — showing live progress and producing downloadable results.
How we built it
Synkron takes uploaded user data and runs it through six AI agents — each performing a unique step from data exploration to insight generation — showing live progress and producing downloadable results.
Challenges we ran into
Coordinating agent communication, removing default/dummy data behavior, and designing a clean but rich UI in a short time were some of the biggest challenges.
Accomplishments that we're proud of
We created a fully working, real-time multi-agent system with a professional interface, fully cloud-integrated, and highly adaptive to different user inputs.
What we learned
We learned how to structure multi-agent systems using ADK, deploy them on Google Cloud, and balance both technical complexity and user-friendly design.
What's next for Synkron
We plan to add customizable agent workflows, user accounts, more export formats, and open-source parts of the code to help others build on top of this system.
Built With
- adk
- bigquery
- csv
- framer-motion
- google-cloud-run
- javascript
- json
- lovable
- python
- react
- rest-api
- supabase
- tailwind-css
Log in or sign up for Devpost to join the conversation.