Tushar Kumar@tuxhar_0

Events attended

Submissions made

India

1 year of experience

About me

Learning 😐

Socials

🤝 Top Collaborators

I’m Anubhav Paul, a student passionate about building a career in Artificial Intelligence and Machine Learning, with a strong focus on solving real-world problems using modern AI systems. I work on developing systems like recommendation engines, chatbots, and RAG-based applications that help improve user experience and decision-making. My approach involves using LLMs, Retrieval-Augmented Generation (RAG), advanced RAG techniques, and machine learning to create scalable and efficient solutions. With my academic background and continuous hands-on learning, I’ve developed strengths in critical thinking and problem-solving, allowing me to approach challenges with a structured and analytical mindset. I focus on turning ideas into working systems that create value. I believe in learning by building and experimenting, and I’m constantly exploring new ways to apply AI in impactful domains. Currently, I’m open to internships, research opportunities, and entry-level roles in AI/ML, where I can contribute, learn, and grow in a fast-paced environment.

Sampad Panda

Bhumicka Das

UX & Graphic Designer passionate about creating intuitive, user-centered, and visually impactful digital experiences. Skilled in blending creativity with functionality to deliver clean and engaging designs.

🤓 Latest Submissions

Neural Analytics

An AI-powered analytics platform that lets you upload CSV files and ask natural language questions. Supports multi-table querying with automatic JOINs, semantic schema search, and AI-generated insights with interactive visualizations. Drag-and-drop CSV upload — Upload up to 5 files (40 MB each) instantly Multi-table NL querying — Ask questions across multiple datasets with automatic JOINs Zero SQL knowledge required — LLM generates correct queries from plain English Semantic schema search — FAISS embeddings find relevant columns by semantic meaning Auto-fix on failure — LLM self-corrects failing queries in real-time Interactive visualizations — Auto-selects best chart type (bar, line, pie, histogram) AI summaries — 3-bullet findings generated from query results Data cleaning report — Shows nulls normalized, duplicates removed, type coercions

Hackathon link

19 May 2026

AIRA - Autonomous Incident Response Agent

AIRA (Autonomous Incident Response Agent) is an AI-powered incident response automation platform that revolutionizes how teams handle production incidents. Built with FastAPI, React, and LangGraph, AIRA receives incidents from monitoring tools like Datadog or Prometheus and executes a sophisticated 5-phase workflow powered by Groq's Llama 3.3 70B LLM. The system automatically classifies incident severity (P0-P3) in under 5 seconds, fetches relevant code context via MCP servers, analyzes similar historical incidents using Redis-based similarity search, generates git-style patches with unit tests, and calculates a composite confidence score. Based on this score, AIRA either automatically creates GitHub pull requests (>85% confidence) or requests human approval via Slack. With enterprise-grade security features including blocked paths for critical files, complete audit trails, and mandatory human oversight for P0 incidents, AIRA achieves 80% faster resolution times while maintaining safety. The real-time WebSocket dashboard provides full transparency into agent decisions, and the system continuously learns from each incident to improve future responses. AIRA reduces incident resolution time from hours to seconds, saves $4,000/hour in downtime costs, and cuts on-call burden by 60%—all while maintaining 95% accuracy in severity classification.

Hackathon link

17 May 2026

👉 Upcoming Hackathons

Web Data UNLOCKED Hackathon

Learn how modern AI agents interact with the live web through hands-on workshops, real infrastructure, and a community builder weekend in San Francisco. 📅 May 25–31, 2026 • May 25 – 30: Online Build Phase • May 30: Hybrid Build Day (Online & Onsite) • May 31: Demos & Awards (Online & Onsite) 🌍 Hybrid event. Join online from anywhere or build onsite in San Francisco. 🚀 The onsite experience will take place during the opening of Bright Data’s new SF space, The Web Data Loft. 📍 On-site Venue (May 30–31): The Web Data Loft 625 2nd St, San Francisco, CA 🏆 $5,000 cash prize + Bright Data AI Startup Program opportunities 🍕 Free food, drinks, networking, workshops, mentorship, and live demos 🧑‍💻 Apply now to build AI agents powered by real-time web access.

2026 May 25

👌 Attended Hackathons

IBM Bob Hackathon

Build solutions that improve how software is built. Work with an AI that understands your codebase, helping you reduce repetitive work and build with real context. ⏳ Build your project in 48 hours. 🚀 Get hands-on with IBM Bob and explore how AI fits into real development workflows before it becomes standard. 💡 Build tools and workflows that developers would actually use. ⭐ Learn directly from experts throughout the event. 🤝 Join a team or build solo. 💰 Prize pool: $10,000 🧑🏻‍💻 Register before the Kick-Off Stream and start building with Bob.

Transforming Enterprise Through AI

📅 May 11–19, 2026 • May 11 – 19: Online Build Phase. • May 18 (Hybrid Build Day – Online & Onsite) • May 19 (Demos & Awards – Online & Onsite) 🌍 Hybrid event. Join online from anywhere or build onsite at the venue. 🏆 Winners will be announced live on stage at the AI & Big Data Expo North America on May 19 📍 On-site Venue (May 18–19): San Jose McEnery Convention Center, CA, USA 🤝 Join solo or with a team. 🎟 FREE AI & Big Data Expo North America ticket included for participants that are able to join the on-site phase. 🏆Compete for a $10,000 prize pool 🧑‍💻 Apply now to design, prototype, and showcase enterprise-ready innovation.