Karan Agrawal@karan_agrawal270
1
Events attended
1
Submissions made
India
1 year of experience
About me
Karan is a B.Tech Computer Science student specializing in Artificial Intelligence and Machine Learning, with a strong focus on Generative AI. Skilled in Python and currently expanding expertise in C++, he enjoys building innovative solutions that merge creativity with technical depth. He has hands-on experience with Google Cloud Generative AI Studio and actively explores applications of AI in education, robotics, and scalable cloud systems. Karan thrives in hackathon environments where rapid prototyping, teamwork, and impactful ideas come together to solve real-world challenges. Key Skills: Generative AI & Applied Machine Learning Python Programming Learning and applying C++ fundamentals Cloud-based AI solutions & data analytics
🤝 Top Collaborators
.png&w=640&q=75)
🤓 Latest Submissions
Hybrid Token-Efficient Router
The Hybrid Token-Efficient Routing Agent is an AI system that intelligently routes user prompts to the most cost-effective Fireworks AI model capable of answering accurately. Unlike naive single-model approaches, our system analyzes each prompt's task type and complexity to select the optimal model, reducing token consumption by up to 60%. Our multi-stage pipeline classifies prompts into 8 categories (factual knowledge, math reasoning, sentiment analysis, summarization, NER, code debugging, logical reasoning, and code generation), estimates complexity, and routes to the cheapest sufficient model. The system prioritizes Gemma models for bonus points, with automatic fallback to MiniMax M3 ($0.3/M input tokens) or Kimi K2.7 Code for code-focused tasks. The result: 74% accuracy on practice tasks using only ~3,500 tokens for 8 tasks—significantly less than using a single large model. The system includes prompt optimization to remove filler words, reducing input tokens by 15-20%.
13 Jul 2026
