Samyukth Kalathil@samyukth_kalathil254

BullRun is a multi-agent options trading system built for the Alpaca AI Trading Agents Hackathon. It runs a 4-stage pipeline: Scout detects market regime (BULLISH/BEARISH/NEUTRAL/VOLATILE), Quant selects defined-risk options spreads (bull call or bear put), a deterministic Risk Engine validates against 12 hardcoded safety gates, and CIO generates a plain-English trade thesis via GPT-4o-mini. The core insight: most trading agents optimize for autonomy. BullRun optimizes for accountability. The LLM never decides whether to trade — it only explains. Python does all math, validation, and execution. The human authorizes. Every decision is SHA-256 hash-chained for tamper-evident audit. During testing, the AI proposed using 18% of the portfolio despite a 2% allocation limit. Prompt instructions were not enough. We rebuilt it so safety is architectural, not behavioral — 12 deterministic gates the AI cannot override, including a 2% per-trade risk rule, portfolio heat cap, correlation guard, time-of-day guard, daily loss circuit breaker, and drawdown halt. Missing data defaults to REJECT, not PASS. BullRun connects to Alpaca's Trading API via alpaca-py for real multi-leg options execution with atomic fill verification. It includes an MCP server for AI tooling integration, a Next.js dashboard with TradingView charts, automated position monitoring with 7 exit rules, and a teaching engine that explains every decision in plain English.

UAE Expat Navigator is a RAG-powered AI assistant built to help UAE residents and expats navigate government services — driving license conversion, visa status changes, work permits, and family residence permits. The system retrieves answers exclusively from official UAE government PDFs (RTA, ICP, MOHRE, GDRFA) and uses conditional tool calling to check eligibility and calculate fees in real time. Architecture: - Frontend: HTML/JS chat interface with tool-call visualization and source citations - Backend: FastAPI with LangChain agent and ChromaDB vector store (185 chunks) - LLM: Qwen 2.5 7B Instruct served via vLLM 0.17.1 on AMD MI300X - Embeddings: OpenAI text-embedding-3-small - Tools: eligibility_checker and fee_calculator with conditional invocation logic Key technical decisions: 1. Tool results are injected above documents in the prompt with an explicit hierarchy rule — preventing the LLM from hallucinating over missing PDF context 2. Fee calculation is blocked when a country is ineligible for direct exchange, avoiding misleading AED quotes 3. Short vague follow-ups like "What about Pakistan?" are detected and routed to the eligibility tool automatically 4. All answers cite specific PDF sources and include a legal disclaimer Deployed on AMD MI300X via AMD Developer Cloud using the vLLM ROCm 7.2 Quick Start image. The 192GB VRAM on the MI300X handled Qwen 2.5 7B comfortably with room to scale. Built with: Python, FastAPI, LangChain, ChromaDB, vLLM, ROCm, AMD MI300X, Qwen 2.5 7B Instruct.

🌎 Online Hackathon | 💻 Dates: 28 August–4 September 2026 | 🏆 $6,000 Prize Pool Build AI trading agents on Alpaca — autonomous agents and trading apps using Alpaca's Trading API, MCP server and CLI. 🌍 Fully online hackathon. Join and build from anywhere in the world.

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.

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.