Social Engine

Inspiration

We wanted to empower creators to stay ahead of trends by providing a smart assistant that finds the most relevant and viral news in their domain — and helps them understand their audience engagement.

What it does

Social Engine helps creators discover trending topics tailored to their niche, analyze how their content performs, and identify opportunities to boost reach. It combines trend discovery, sentiment tracking, and audience analytics into one simple dashboard.

How we built it

We built Social Engine using Python for the backend, with Parallel AI for rapid data collection and relevance scoring. Lightning AI powers our recommendation model for personalized trend suggestions. We used Claude Code for fast code debugging and RedisVL as our vector database for efficient data retrieval and caching.

Challenges we ran into

We quickly ran out of Parallel AI credits, which limited large-scale testing and forced us to optimize API calls and caching.

Accomplishments that we're proud of

We built a working prototype capable of surfacing real-time, domain-specific trends and personalized insights in just a few days.

What we learned

We learned how to combine multiple AI and data tools into a cohesive pipeline — from data fetching and vector storage to model-driven recommendations — and how to manage limited resources under hackathon constraints.

What's next for Social Engine

We plan to evolve Social Engine into a full-fledged social media manager agent — one that can not only find trends but also generate and schedule optimized content for creators across platforms.

Built With

• lightning
• python
• redis-vl