Judy Wang@judyailab

Problem. A Taipei SME stuck in Net 60 with a US buyer has no good options: Atradius takes 8 months and 30%, a US attorney costs more than the outstanding, and QuickBooks emails sound like Google Translate. Existing tools assume your CFO speaks American English in the buyer's timezone — false on the Taiwan→US corridor. Solution. Recoverflow is a 9-agent dunning system on Band (8 production + AAA Specialist via Day-65 dynamic peer discovery): Pre-flight 3-path routing (in_spot / lite / attorney_recommended), Investigator pattern-tagging replies, Diplomat cadence-aware emails, Tone Coach (Claude) blocking hostile + FDCPA-non-compliant language, Escalator on Day 65, Voice Agent via ElevenLabs ConvAI + Twilio, Concierge as Slack HITL choke point, Payment Agent settling Circle USDC on real ARC-TESTNET. Outstanding, not gross (D-038). A $47,300 gross invoice the lawyer rejects as "out of sweet spot" is $23,650 outstanding after a 50% deposit — exactly where we operate. Wired through 5 modules across 4 demo Beats including the demand letter. Tech. Python 3.12, Band SDK, Claude Sonnet 4.5 / Haiku 4.5, ElevenLabs ConvAI, Twilio, Circle Programmable Wallets on real ARC-TESTNET (5 verified on-chain tx), Slack HITL, Featherless, Chroma RAG (31 chunks via BGE), pytest 482-test suite. Demo highlights. - Beat 4 — Pre-flight 3-path routing on outstanding balance. - Beat 8 — Welfare 988 SOP: set_anomaly_halt(case_id, "welfare") fires BEFORE Concierge page (life before debt, 3 unit tests). - Beat 9-11 — 5 real Circle USDC tx settled in data/audit_trail.jsonl (475dcb1c…, c6b4fe6b…, 36e503b2…, 2bcfdc5b…, 496dc964…). Track 3 fit. FDCPA language gating, paylink-only demand letters (no AI-hardcoded SWIFT/IBAN), HITL on every outbound, deterministic checkout URLs, 988 priority over debt, ConvAI 16-reason escalation enum, full audit_trail.jsonl chain of custody.

AgenticTrade envisions a future where AI agents move beyond being mediocre generalists by autonomously hiring specialized domain experts. The core barrier to this "Agent Economy" is the friction of traditional Web3 gas fees, which often range from $0.50 to $5.00—mathematically making $0.001 micro-transactions impossible. Our platform solves this on the Arc Network by integrating Circle Nanopayments and the x402 protocol. This infrastructure allows any AI agent (Claude, GPT, or custom) to discover services via MCP or OpenAPI and execute payments instantly with zero gas. To ensure safety, we built a Budget Governor for human-set spending limits, an autonomous negotiation layer for market-driven pricing, and a reputation system to reward reliable buyer agents. AgenticTrade is not just a concept; it is currently running in production on the Arc testnet. To date, our network of 201 agents has processed over 564 real transactions across 180+ API endpoints, proving that sub-cent autonomous commerce is a reality.

JudyAI WaveRider is an autonomous crypto trading agent that proves performance on unseen data, not curve-fit backtests. The Problem Most AI trading agents backtest on the same data they optimize on. This is overfitting. They offer no on-chain proof and treat risk management as an afterthought. Our Solution ‧Walk-Forward Validation: 82.2% win rate across 366 out-of-sample trades using 8 rolling windows (90-day train, 30-day test). Every parameter proven on unseen data. ‧Three Strategy Engines: WaveRider (EMA crossover + RSI + volume), BB Squeeze (Bollinger Band breakout), and MACD Divergence (price-momentum reversal). A 36-cell strategy matrix routes the best strategy per coin per market regime. ‧Dual-AI Ensemble: MiniMax M2.7 + Qwen 2.5 cross-validate every signal. Disagreement = no trade. Rule-based fallback if APIs fail. ‧7-Layer Risk Management: Position sizing, daily loss limit, max drawdown, consecutive loss scaling, per-pair throttle, and regime filter. 87% of raw signals rejected. Result: 0.4% max drawdown over 11 days of adverse markets, preserving 99.6% of capital. ‧ERC-8004 On-Chain Identity: Agent #17 on Sepolia. 79 EIP-712 signed trade intents. 214 validation artifacts with SHA-256 Merkle integrity. Validation 98/100, Reputation 94/100, Rank #5 of 58. ‧Radical Transparency: Live win rate was 40% during ranging markets — we show it alongside the 82.2% backtest. The risk system held losses to $377 on $100K. Capital preservation > cherry-picked demos. ‧Kraken CLI Integration: OHLC data for 7 pairs, real-time tickers, paper trading execution, balance tracking. Fully verifiable: make install && make test && make validate && make verify

📅 June 12–19, 2026 • June 12: Kick-off Stream • June 12–19: Online Build Phase • June 19: Project Submissions Ends 🌍 Fully online hackathon. Join and build from anywhere in the world. 🤝 Build practical enterprise workflows where AI agents communicate, coordinate, exchange context, and complete work together. 🧠 Powered by Band and Codeband, built for collaborative AI systems and agent orchestration. 🏆 Prize Pool: $10,000+ 🧑‍💻 Apply now to build the next generation of enterprise multi-agent systems.

In this hybrid hackathon powered by Arc and Circle, developers will build the next generation of Agentic economic applications using Circle’s Nanopayments infrastructure with settlement on Arc in USDC. For the first time, high-frequency, usage-based transactions between users, APIs, and AI agents can operate without gas overhead eroding margin. Arc provides stablecoin-native settlement with predictable, dollar-denominated USDC fees and deterministic, sub-second finality — enabling real-time coordination and economically viable per-action pricing at scale. 📅 April 20 – 26, 2026 • Apr 20 – 25 (Online): Submit projects by Apr 25. • Apr 25 (On-site Build – SF, CA): Teams refine projects. • Apr 26 (On-site Demos & Awards – SF, CA): Live pitches & winners announced. Get guidance from Arc and Circle experts through on-site support. 📍 On-site Venue (April 25-26): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 🤝 Go solo or team up, it's your flow. 🏆 Compete for a $15,000+ Prize Pool. 📍 Please note: 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. 🧑🏻‍💻 Secure your spot now – sign up before the Kick-Off Stream!

⏱️ Design, build, and deploy trustless AI trading agents. 📅 March 30 – April 12, 2026 🌐 Build AI trading agents that execute strategies using ERC-8004 or Kraken CLI. 🤝 Build solo or in teams to create autonomous trading, risk, yield, or protection agents. 💰 $55,000 prize pool, allocated and shared via Surge and Kraken. Your team should have registered project at early.surge.xyz in order to be eligible for the prize. Get access in your team profile or our discord 🔑 Access to early.surge.xyz If prompted for login credentials, use: • Username: admin • Password: JBRv2xWG7AzwVrLz88