Riccardo Sordi@cACTUS_555

Algorithmic trading systems typically fail in one of two ways: simple quantitative bots buy dips blindly without understanding root causes—often catching falling knives during structural decline—while ungrounded LLM agents hallucinate trade parameters and lack deterministic risk bounds. Phoenix Alpha solves this by enforcing a clean separation of concerns between qualitative AI reasoning and deterministic risk controls. Built natively on Alpaca's API ecosystem, the agent operates in five distinct stages: Quantitative Screener: Queries Alpaca market data to track S&P 100 leaders down over 15% from 52-week highs. Qualitative LLM Triage: Ingests real-time headlines and filings via the Alpaca News API. An LLM agent powered by Groq and Pydantic classifies each selloff as either a Transitory Dip or Structural Failure, validating moat durability with structured JSON schemas. Options Structuring Engine: Transforms validated theses into 20–60 DTE Bull Put Credit Spreads, capturing elevated panic premium while buying lower put wings for disaster insurance. Deterministic Risk Gate: The LLM is strictly prohibited from sizing capital. Pure Python code calculates contract sizing to enforce a hard trade risk cap of ≤ 2.0% of total account equity, rejecting unhedged exposure. Execution & Observability: Dispatches atomic multi-leg orders to Alpaca Paper Trading, monitored via an interactive Streamlit UI displaying Greeks, conviction scores, and live executions. Phoenix Alpha bridges agentic news intelligence with unbreakable mathematical safeguards to deliver a production-grade autonomous trading desk.

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.