Avik Soni@aviksoni54651465

CampusPulse AI is an autonomous student-to-administration liaison and facility tracking platform built to eliminate campus friction. Traditional university maintenance systems are plagued by lost requests, zero transparency, and manual bottlenecks. Built entirely to showcase rapid AI-native development, CampusPulse AI introduces an Intelligent Grievance & Facility Dispatcher workflow: Frictionless Submission: Students report issues (e.g., broken equipment or maintenance problems) using plain, natural language. AI-Powered Triage: Integrated AI agents instantly analyze the text to extract key metadata—automatically categorizing the issue (HVAC, Plumbing, Electrical, IT), determining priority/urgency levels, and drafting formal summaries. Interactive Lifecycle Management: Administrators and users can track and advance ticket status seamlessly through a robust interactive dashboard (from Submission to In Review, Assigned, and Resolved). Designed with a clean, modern interface and persistent state management, CampusPulse AI demonstrates how quickly an everyday real-world problem can be transformed into a functional, cloud-ready product using modern AI-driven building blocks.

Most routers pick a model per task-type and hope. Penny treats every task as its own cost problem: it first tries a sandboxed local engine (math/units/regex/dates) for a free answer, then a zero-token heuristic estimates how capable a model the task actually needs, then it computes real blended cost (live Fireworks pricing × this task's estimated prompt/output size) across the whole catalog and picks the cheapest one that clears that bar. Answers are checked for free — labels validated, JSON parsed, generated code actually executed against the task's own test cases — and only escalate to a pricier model on a genuine failure signal, capped so it can't runaway. Prompts are short and category-specific with tight output budgets, because efficiency is as much about not paying for a paragraph as it is about which model answers.

🌎 Hybrid Hackathon | 💻 Online Build: October 16–19, 2026 | 📍 On-site: October 19–20, 2026 The official hackathon of AI & Big Data Expo Europe, organized by TechEx Events and lablab.ai. Build AI applications and agents across AI, cybersecurity, cloud, IoT, automation, edge computing, digital transformation, and data infrastructure, then showcase your project live at one of Europe's largest enterprise technology events. 📍 On-site Venue (October 19–20): RAI Amsterdam Europaplein 24, 1078 GZ Amsterdam, Netherlands 📍 If approved for the on-site experience, you'll also have the opportunity to showcase your project live. Travel and accommodation will not be covered.

🌎 Hybrid Hackathon | 💻 Online Build: September 10–16, 2026 | 📍 On-site: September 15–17, 2026 The official hackathon of AI Infra Summit — co-organized by Kisaco Research and lablab.ai. Build production-grade AI applications on the modern AI infrastructure stack, alongside 8,000+ attendees, researchers, founders, and infra leaders. 📍 On-site Venue (September 15–17): Santa Clara Convention Center 5001 Great America Pkwy, Santa Clara, CA 📍 On-site participation is by invitation only. Travel and accommodation expenses will not be covered.

🌎 Online Hackathon | 📅 August 3–10, 2026| 💻 Powered by native.builder The official native.builder hackathon, hosted by NativelyAI and lablab.ai. Join founders, developers, designers, and builders to create real AI-native applications powered by native.builder: from idea to deployed product, fully in the cloud. 💻 This hackathon is fully online. No travel required.