Nikhil Pande@pandenikhil524159

Token Frontier Router — a general-purpose AI agent for AMD Developer Hackathon ACT II, Track 1. Routes 8 task categories (factual Q&A, math, sentiment, summarization, NER, code debug/gen, logic) through Fireworks AI models, minimizing token spend while clearing an 80% LLM-judge accuracy gate. Built with a record-then-replay evaluation harness (frontier tracing, per-category gate policy, judge-proxy validation) to calibrate model choice and prompt design before every submission — architecture and gate survived two scoring-rule changes (accuracy-first, then no-local-tier) intact. Verified 89.5% (17/19) at 6,351 tokens on live evaluation; an isolated logic-template fix is staged and tested pending resubmission. Zero-dependency Python, Dockerized (linux/amd64), all inference routed through FIREWORKS_BASE_URL per competition rules.

VoltWise AI helps Indian households understand and optimize their electricity bills through explainable AI, OCR-powered bill extraction, and deterministic tariff analytics. The platform processes real electricity bill PDFs — including Marathi MSEDCL bills — and converts them into structured energy intelligence dashboards. Instead of only showing the final payable amount, VoltWise breaks down energy charges, wheeling charges, fuel adjustment costs, taxes, and tariff slab impact in a transparent and user-friendly way. Key capabilities include: Multilingual bill extraction (English + Marathi) OCR and layout-aware PDF parsing Deterministic tariff computation engine Explainable energy-cost analysis Consumption trend insights Bill reconciliation between extracted and computed values Simulation engine for “what-if” energy savings scenarios Optimization recommendations for reducing monthly costs The architecture combines: FastAPI-based AI and extraction services OCR pipelines using PyMuPDF + Tesseract Structured tariff computation engine Explainability layer for energy cost interpretation Next.js frontend for interactive visual analytics One of the core innovations is separating: Extracted bill-stated values Computed tariff-estimated values This allows the system to both: faithfully represent what the utility charged, and independently analyze whether the bill structure is optimal or anomalous. VoltWise AI is designed as the foundation for a scalable energy-intelligence platform for emerging markets where electricity bills are complex, multilingual, and poorly understood by consumers. Potential future applications: AI-powered household energy advisors Utility anomaly detection SME energy optimization Green-energy transition analytics Smart home integrations

To participate in the hackathon, simply click Sign up with AMD. If you are not already a member of the AMD AI Developer Program (ADP), you will need to create an account. ADP members can access AI tutorials, experts, and community support. In addition, new members can claim a free month of DeepLearning.ai pro, $100 in AMD GPU cloud credits, and $50 in Fireworks AI API credits. All hackathon participants will receive on hackathon launch additional compute and API credits for their projects. Ready to build what's next on AMD? Sign up with AMD below to secure your spot.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.