Hakim Gh@hakimkt

KT is a voice-first AI tutor that transforms learning from a text-based activity into a natural conversation. Traditional AI learning tools often require students to type questions, read lengthy answers, and decide what to ask next. KT removes that friction. Students simply speak to KT as they would speak to a teacher. KT listens in real time, understands the learner's question, responds naturally through voice, and keeps the conversation going. Built using AssemblyAI's real-time voice technology, KT can explain difficult concepts, simplify explanations, provide examples and analogies, ask follow-up questions, quiz learners, and help them practice spoken English. Rather than simply giving answers, KT is designed around an interactive teaching approach: explain, ask, listen, adapt, and reinforce. A learner can say, "I don't understand," and KT can immediately try a simpler explanation. It can ask the learner to explain an idea back in their own words, helping turn passive listening into active learning. KT is designed as a lightweight, serverless application that can run on Vercel without requiring a database for the core experience. The goal is to make high-quality AI tutoring as accessible and natural as having a conversation. KT's vision is simple: make learning something you can just talk about. KT — The AI Tutor You Talk To.

Options Sniper is a fully autonomous Bull Call Spread paper-trading agent built for the Alpaca Options Alpha Agents hackathon. It discovers, evaluates, and executes options spread opportunities using 13 Alpaca API endpoints — zero database, zero external AI, zero paid services. DYNAMIC MARKET DISCOVERY replaces static watchlists. Each tick fetches top gainers, losers, and most-active stocks from Alpaca's screener, qualifies them for options availability and momentum, and merges with a default watchlist — capped at 15 sniper candidates. OPTIONS INTELLIGENCE enriches each spread using Alpaca's option snapshots: Greeks (Delta, Gamma, Theta, Vega), IV, volume, OI, and bid/ask spreads. A 0-100 Quality score (spread 40pts + OI 30pts + volume 20pts + IV sweet spot 10pts) adds +0 to +10 to the opportunity score. NEWS & CORPORATE ACTION RISK checks Alpaca's news and corporate-actions APIs before trading. Sentiment is classified via deterministic keywords (no LLM): positive (beat, upgrade, rally) vs. negative (miss, lawsuit, SEC probe). Corporate actions — dividends, splits, mergers — are flagged when ex-dates are near. Impact ≤ -5 rejects the trade. News adds -5 to +5 to the score. AGENT FLOW: Account → Discovery → News/CA Risk → Options Chain → Greeks/Liquidity → Score → Risk Check → Paper Order → Monitor → Auto-Exit. Score 0-120: trend 25, RSI 20, momentum 20, liquidity 15, risk/reward 20, options quality +10, news ±5. Entry requires score ≥ 75, risk ≤ 1% equity. Auto-exit: +25% profit, -20% loss, ≤7 DTE, or bearish reversal. Mleg orders with slippage cushion. Short legs close first to avoid 403 errors. The Alpaca Monitor shows every API call — endpoint, latency, status, sanitized responses — in a 7-step pipeline. Paper trading enforced by hard URL guard. Full mock mode for keyless demos. Next.js 15, React 19, Tailwind 4, Vercel. Serverless. Stateless. Alpaca is the source of truth.

AuditPilot AI is an AI-powered cybersecurity compliance auditing platform designed to simplify and accelerate security assessments across multiple industry frameworks. It transforms traditional manual audit processes into an intelligent, interactive, and automated experience where organizations can evaluate their security posture, identify compliance gaps, and receive actionable remediation guidance. The platform enables users to select their industry, organizational profile, and desired compliance framework such as GDPR, PCI-DSS, HIPAA, ISO 27001, and other security standards. Based on the selected framework, AuditPilot AI dynamically generates relevant assessment scenarios, control checks, and audit questions aligned with industry best practices. Using AI-driven analysis, AuditPilot AI evaluates responses, maps findings against compliance requirements, calculates risk levels, highlights control deficiencies, and provides recommendations to improve security maturity. It assists auditors, security teams, and organizations in performing faster assessments without requiring extensive manual checklist management. AuditPilot AI brings together compliance intelligence, risk assessment, and security governance into a single platform, helping organizations move from reactive audits to continuous compliance readiness.

SignalSniper is an AI-powered financial intelligence platform designed to help traders understand market signals with clarity and confidence. It analyzes Forex indicators such as RSI, MACD, Bollinger Bands, moving averages, and market patterns to explain possible market direction. Unlike traditional tools that only provide BUY, SELL, or HOLD signals, SignalSniper AI delivers explainable insights including signal reasoning, confidence level, market trend, risk assessment, entry guidance, stop-loss, take-profit, and key factors influencing the decision. The platform is built on a multi-agent AI architecture where specialized agents analyze different market perspectives, including signal validation, risk management, contrarian analysis, market context intelligence, historical pattern analysis, and final decision orchestration. These agents collaborate to generate balanced, reliable, and risk-aware trading intelligence. SignalSniper Score™ Engine calculates a proprietary trade intelligence score and generates a professional AI Trade Brief in HTML and Markdown from multi-agent analysis. SignalSniper AI combines technical analysis with generative AI to transform complex financial data into easy-to-understand insights, helping traders improve their analysis process and make more informed decisions. The Multi-Agent Decision Orchestrator combines individual agent outputs into precise trading intelligence while reducing single-model dependency through collaborative AI reasoning. SignalSniper AI demonstrates the use of artificial intelligence in FinTech by making market analysis more accessible, transparent, and user-friendly. It uses a hybrid AI architecture powered by Fireworks GPT, self-hosted Gemma running on AMD ROCm-accelerated PyTorch with vLLM. A Gemma fallback ensures reliable analysis availability, enabling scalable AI deployment for algorithmic trading and intelligent decision support systems.

Six Matches. One leaderboard. Build on AMD, earn points and compete for prizes.

🌎 Hybrid Hackathon | 💻 Online Build: 3–8 November 2026 | On-site Phase: 8 November 2026 📍 On-site Venue: Pierpont Place 163 W Pierpont Ave, Salt Lake City, UT 84101, USA ✨ Please note that travel and accommodation are not covered.

🌎 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: 12-17 October 2026 | On-site phase: 17-18 October 2026 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. The AMD Developer Hackathon: ACT III is a hands-on event for developers, founders, engineers and builders who want to push what’s possible with AI on real infrastructure. 📍 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.

🌎 Online Hackathon | 💻 Online Build: Sept 26 - Oct 5, 2026 A virtual, global hackathon. Build from anywhere in the world. Dark Factory is the official hackathon of WeAreDevelopers World Congress North America, presented by BAND, but you don't need to be in San Jose to take part. For one week, you build a software factory in BAND Desktop: a band of coding agents that plans work, implements it and checks its own results. 🎟️ Bonus for sign-ups: you are eligible for a free ticket to WeAreDevelopers World Congress North America in San Jose (Sep 23–25). If you do go, stop by the BAND booth: a surprise is waiting for you.