StratIQ

Homepage
Inside chatbot
Analysis
Phase breakdown
player focus
Coach Insights

Inspiration 💡

Competitive gaming and esports generate a massive amount of performance data 📊, but coaches and analysts often struggle to convert this data into clear, actionable insights during or after matches. Most tools focus on raw statistics, which require deep manual analysis and domain expertise to interpret.

StratIQ was inspired by the need to bridge this gap — to create a system that not only shows performance metrics but also explains what they mean 🧠 in a way that supports faster, better decision-making for coaches and analysts.

What it does 🎯

StratIQ is an AI-powered performance intelligence dashboard that transforms structured match data into explainable insights.

The platform allows users to:

📈 Explore player and match performance across different game phases
🧮 Understand trends using metrics like kills, damage dealt, KAST, and round impact
🎮 View insights through an interactive, gamified dashboard
🤖 Prepare the foundation for an AI coach assistant that answers performance-related questions transparently

The focus is not just analytics, but explainability and confidence in insights ✅.

How we built it 🛠️

StratIQ was built using a modern, scalable full-stack architecture with JetBrains IDEs as the primary development environment.

🐍 Backend: Python with FastAPI, developed using PyCharm, for data ingestion, feature extraction, analysis, and insight generation
⚛️ Frontend: React with TypeScript and TSX, developed using WebStorm, for building interactive dashboards and UI components
🎨 Styling: CSS and Tailwind for a clean, esports-inspired interface
🗂️ Data Handling: Structured CSV and JSON demo data simulating real match statistics
🚀 Deployment: Frontend deployed on Vercel for live demos and easy access

Using JetBrains IDEs allowed us to efficiently navigate a multi-language codebase, safely refactor components, and maintain code quality while iterating quickly under hackathon constraints.

Challenges we ran into ⚠️

One of the biggest challenges was managing complexity across the full stack within a limited hackathon timeframe ⏱️. This included:

Designing a backend that could support explainable analytics instead of just raw numbers
Keeping frontend state, data flow, and visualizations consistent and easy to understand
Mapping structured match data into meaningful insights without overfitting or overclaiming
Debugging TypeScript type issues and FastAPI response mismatches while iterating quickly

Another challenge was ensuring that the project remained clear and demo-ready 🎥 without becoming overly complex or fragile under time pressure.

How Jennie (JetBrains AI) helped 🤝

JetBrains AI (Jennie), integrated directly inside the JetBrains IDEs, played a key role in accelerating development and reducing friction across the stack.

🧩 Helped debug FastAPI endpoints by explaining request/response mismatches directly in the editor
🔄 Assisted in refactoring Python data-processing logic to improve readability and maintainability
🧠 Provided TypeScript and TSX suggestions in WebStorm to resolve typing issues and component structure problems
📝 Helped generate boilerplate code, API schemas, and inline documentation faster

Jennie acted as a context-aware coding assistant, enabling faster iteration while preserving developer understanding and control ⚡.

Accomplishments that we're proud of 🏆

✅ Built a complete, working full-stack analytics platform within hackathon constraints
🔍 Designed explainable analytics instead of a black-box system
🌐 Successfully deployed a live, interactive dashboard
🎯 Maintained a clear product vision while handling both backend and frontend development