Ben Kim@Lmentrics

DeltaMind AI is an autonomous options-trading agent built for the Alpaca AI Trading Agents Hackathon. It runs a real-time decision pipeline, orchestrated with LangGraph, that watches a curated basket of liquid, options-active symbols and evaluates one full decision cycle per symbol on every bar-close. The core design principle is gating cheaply before spending anything. A deterministic, hand-written technical screener has to confirm real momentum confluence, trend alignment on an hourly timeframe combined with a fresh crossover on a faster one, before a single LLM call is ever made. Only setups that clear this bar reach the AI layer, where Featherless AI (running Kimi K2 Instruct) acts as a lead strategist: not a rubber stamp, but a genuine contradiction check against live sentiment and news context. Every approved setup then passes through a second, entirely deterministic gate, a risk module with zero LLM calls in it, enforcing hard position-size, sector-concentration, margin, and stop-loss limits before anything reaches the brokerage. Nothing is ever forced through: a rejected setup is always logged with its exact reason, so the system's behavior is fully auditable, not a black box. Execution itself runs through Alpaca's official MCP Server, so every live order carries a structured, inspectable tool-call trail, while high-frequency market data uses direct REST for latency. A lightweight CLI wrapper handles low-overhead scheduled account checks. The whole system runs live and continuously against a fresh $100,000 Alpaca paper account, deployed on Render (backend) and Netlify (frontend), with a real-time dashboard for configuration, live logs, historical backtesting, and full decision-history transparency — including every rejected trade and the reasoning behind it.

5% to 15% of all commercial freight invoices contain carrier billing errors—costing mid-market shippers up to 7% of their annual freight budget in unchecked overcharges. AuditFlow.ai is an autonomous, AI-driven freight invoice audit and discrepancy recovery platform built entirely within Native Builder to eliminate this financial leakage. By combining multimodal AI vision models and agentic remote web scrapers, AuditFlow.ai transforms days of manual accounts payable auditing into a 2-second automated workflow: 1. Featherless AI (Multimodal Vision OCR): Instantly extracts line-item billing data (base rates, fuel surcharges, liftgate fees, weights) from uploaded carrier PDFs and scanned invoice images. 2. Bright Data (Agentic Remote MCP Web Scraper): Performs real-time web verification against official EIA Diesel Index data and carrier web portals to validate fuel surcharges and tariff compliance. 3. Speechmatics (Voice Dictation): Enables AP audit managers to dictate voice notes directly into dispute logs hands-free. 4. Autonomous Dispute Engine & Supabase Sync: Calculates exact rate card discrepancies, generates legally defensible dispute email packages, updates Supabase records, and tracks recovered capital in real time. AuditFlow eliminates billing leakage, recovers thousands in overcharges, and empowers AP teams with 100% defensible claims.

AeroClaw is an end-to-end, autonomous B2B procurement platform designed to eliminate modern supply chain paralysis caused by manual inventory monitoring and sluggish email negotiations. The architecture relies on a highly secure, local background daemon running an intelligent File Watcher that monitors enterprise inventory files in real-time. The moment a stock shortage is flagged, the system deploys targeted Price Crawler subagents to securely scan competitive market portals and extract the best live procurement rates. This data is instantly fed to our proprietary CFO Negotiator agent, which mathematically optimizes and drafts human-like proposals for supplier outreach. Built for the enterprise, the platform features a real-time analytics overview dashboard with an interactive negotiation delta slider, giving operators complete visibility over margin controls. To guarantee absolute security, a human-in-the-loop consent gate ensures no proposal is dispatched without formal internal approval, successfully bridging the gap between raw warehouse status and live market intelligence.

🌎 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.

🌎 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.