• 

  Smart Suggest and Refine Feature

• 

  Slack Macros

• 

  Homepage

About the Project: Maqro

Inspiration

We noticed that even the most tech-savvy users often waste time repeating the same actions—copying files, formatting text, switching between apps—without realizing how much it adds up. Inspired by this hidden inefficiency, we built Maqro to unlock a smarter, more automated way of working by learning from what you already do.

What We Learned

Through this project, we deepened our understanding of user behavior analysis, system-level event tracking, and the fine balance between automation and user control. We also explored machine learning models for pattern detection and learned how small UX choices can massively affect user trust and adoption.

How We Built It

• Tracking Engine: We used low-level APIs to capture keystrokes and mouse movements securely across macOS and Windows.
• Pattern Analysis: We built a lightweight local analyzer that detects repetitive sequences without sending any data to the cloud, ensuring privacy.
• Macro Suggestion System: Based on detected patterns, Maqro suggests macros using a smart ranking algorithm that considers frequency, complexity, and time savings.
• UI/UX: We designed an intuitive dashboard where users can review suggested macros, customize them, and choose to activate or discard them.

Challenges We Faced

• Privacy and Security: Capturing input data while maintaining strict local-only processing was challenging but critical for trust.
• Noise Filtering: Differentiating meaningful patterns from random noise required careful tuning of our detection algorithms.
• Cross-Platform Support: Handling different event systems across macOS and Windows added significant complexity.
• User Experience: Making macro suggestions feel helpful, not intrusive, took multiple iterations based on user feedback.

Built With

• electron
• fetch.ai
• python
• react