Mutshidzi Sathekge@Mutshidzi

Breeze Trading is an autonomous options trading agent engineered for the Alpaca API that strictly decouples probabilistic intelligence from deterministic execution. Built to eliminate model hallucination and emotional bias, the system operates on a zero-trust architecture: pure Python handles pattern detection across a targeted 10-symbol universe, a multi-agent LLM layer conducts retrieval-grounded directional debate, and an immutable, hardcoded Python risk gate retains absolute veto power over every execution. Trade generation begins with an unyielding top-down bias gate, requiring complete Daily-to-4H trend alignment before scanning for low-timeframe continuation flags or 1H breakout-and-hover reversals. No setup is advanced without confirmed higher-timeframe agreement, and no trade executes without passing strict algorithmic limits on portfolio Greeks, liquidity, and downside exposure—ensuring every position is quantitatively validated, mechanically governed, and fully auditable from signal to fill.

KasiBiz Lite is a mobile-first business companion built for South Africa's township and informal-sector entrepreneurs — spaza shop owners, hair salons, general dealers, and street vendors who currently track their business in a notebook or from memory. Owners sign up with just a phone number and a PIN, no email required. From there, recording a sale or an expense takes just a couple of taps from any smartphone browser. The dashboard shows today's sales, expenses, and net position at a glance, so owners always know where they stand. The standout feature is AI Insights: on every dashboard load, a Supabase Edge Function pulls the shop's real sales, expense, stock, and trend data, then sends it to Groq's Llama 3.1 model, which turns the raw numbers into a plain-language daily summary — top sellers, low-stock alerts, slow-moving products, and week-over-week trends. No accounting jargon, no spreadsheets, just clear guidance an owner can act on immediately. The entire application — authentication, database schema, UI, and workflow logic — was built primarily using native.builder, with Supabase powering auth and data, and Groq powering the AI reasoning layer. It's deployed to a publicly accessible URL and fully functional end-to-end, from signup through to AI-generated business insights.

Every engineering team faces the same problem: logs and alerts flood in constantly, and someone has to manually judge what's actually serious. That triage step wastes time, distracts engineers from real work, and doesn't scale as systems grow more complex. Sentinel automates this first, most tedious step of incident response using a hybrid AI architecture designed to balance cost and accuracy. At its core is a Gemma 2 model that I personally fine-tuned using LoRA on an AMD Instinct MI300X GPU. This local model handles the vast majority of incoming logs instantly and completely free of charge, classifying severity, category, and providing a short explanation. Only when this local model's confidence is low does Sentinel escalate the log to a larger, more capable reasoning model — Kimi K2.7 Code — through the Fireworks AI API. Every single classification, along with which model handled it, is saved to a database and displayed on a live dashboard. This gives teams a direct, measurable view of their cost savings: exactly what percentage of incidents were resolved for free locally versus how many required the more expensive remote model. Unlike many AI hackathon projects that simply wrap a single API call in a chat interface, Sentinel's core innovation is its routing decision layer — a genuinely fine-tuned model making real-time, defensible tradeoffs between cost and accuracy. This entire system, from model fine-tuning to inference to the user-facing dashboard, runs on AMD compute, and is fully containerized with Docker for easy deployment. This isn't just a hackathon prototype — the same architecture could plug directly into real-world alerting pipelines like PagerDuty, Datadog, or Slack integrations, immediately reducing both AI inference costs and mean-time-to-triage for engineering teams of any size. It solves a problem every company running infrastructure genuinely has.

🌎 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.

🌎 Hybrid Hackathon | 💻 Online Build: September 10–16, 2026 | 📍 On-site: September 15–17, 2026 The official hackathon of AI Infra Summit — co-organized by Kisaco Research and lablab.ai. Build production-grade AI applications on the modern AI infrastructure stack, alongside 8,000+ attendees, researchers, founders, and infra leaders. 📍 On-site Venue (September 15–17): Santa Clara Convention Center 5001 Great America Pkwy, Santa Clara, CA 📍 On-site participation is by invitation only. Travel and accommodation expenses will not be covered.

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.