{
  "id": 10221347,
  "title": "🥇 We Won Best Use of Snowflake at ELEMENTX 2026 ❄️ | MLH Hack Day 💻",
  "url": "https://urgent.news/2026/09/27/we-won-best-use-of-snowflake-at-elementx-2026-mlh-hack-day",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-09-27T13:36:03.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/abdullahlko/we-won-best-use-of-snowflake-at-elementx-2026-mlh-hack-day-chj"
  },
  "original_language": "en",
  "account": "The ELEMENTX 2026 hackathon, hosted by the Department of CSE at Integral University in Lucknow, concluded with the team emerging victorious in the Best Use of Snowflake category. This achievement came with a Machine Learning Kit and a .xyz domain from XYZ, all of which were enthusiastically received by the team.\n\nThe team tackled Problem Statement 02: From Signal to Decision, which focused on the challenge of enterprise IT and FinOps downtime costing up to $9,000 per minute. The team's solution was an AI-powered incident copilot named ResolveIQ, designed to streamline the incident resolution process by gathering pertinent information and guiding engineers towards an effective response.\n\nResolveIQ leverages Snowflake Cortex AI to analyze incident context, generating a structured Root Cause Analysis (RCA) complete with source references. The team incorporated privacy measures to handle sensitive information and developed an incident command center that tracks SLA compliance and facilitates remediation efforts.\n\nThe public repository behind ResolveIQ has since transitioned to utilizing Groq AI for LLM inference, although the core Retrieval-Augmented Generation (RAG) and incident-resolution workflow remains intact. The RAG pipeline functions by processing runbooks and historical tickets, employing sentence transformers and FAISS for semantic search, ultimately leading to an AI-driven Root Cause Analysis and subsequent remediation steps.\n\nThe user interface for ResolveIQ moves beyond a conventional chatbot, incorporating features such as a live incident stream, SLA countdowns, AI search capabilities, evidence presentation with source references, diagnostic and knowledge modes, and a remediation terminal. This comprehensive interface empowers engineers to transition from incident investigation to understanding critical evidence and deciding on the necessary actions.\n\nThe technology stack supporting ResolveIQ includes Snowflake Cortex AI for AI analysis, Groq for backend processing, FastAPI as the backend framework, RAG components built using LangChain, FAISS, and Sentence Transformers, and a frontend developed with React, Vite, and Tailwind CSS.\n\nReflecting on the experience, the team emphasized that building an AI application involves more than just selecting an LLM. Key aspects of the engineering process revolved around retrieving relevant context, ensuring responses are grounded in source material, managing sensitive data, and converting AI outputs into actionable insights for engineers.\n\nThe team's success in the Best Use of Snowflake category at ELEMENTX 2026 is a testament to their collaborative efforts, with Arshil Masood, Kamran Rizvi, and Ayushmaan Vaibhav all contributing significantly to the project. Their dedication to refining ideas, troubleshooting issues, and persevering until they delivered a solution worthy of acclaim has made this hackathon an unforgettable experience.",
  "summary": "We won Best Use of Snowflake at ELEMENTX 2026 , an MLH Hack Day hosted by the Department of CSE, Integral University, Lucknow! 🥳 Taking the top spot also came with a Machine Learning Kit 🛠️ and a .xyz domain 🌐 from XYZ. Definitely something we're super happy to receive! 😊 🚨 The $9,000/Minute Problem In enterprise IT and FinOps, downtime can cost upwards of $9,000 per minute . When an…",
  "key_points": [
    "ELEMENTX 2026 hackathon awarded Best Use of Snowflake to team",
    "ResolveIQ AI incident copilot streamlines enterprise IT and FinOps downtime",
    "Team comprised Arshil Masood, Kamran Rizvi, and Ayushmaan Vaibhav"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}