Another late night. Building a quant trading system an agentic model where different AI agents handle research, testing and risk, and none of them is allowed to place a trade on its own.
The hardest part so far? Being honest when the results say "not yet." Most strategies I've tested failed once real costs were included. That's exactly what testing is for.
Keeping The Psychology of Money and The Diary of a CEO close while I figure it out. What are you reading these days?
Curious how you’ve separated the agents from execution. When you say none can place a trade on its own, is that enforced through a separate execution service with fixed risk checks, human approval or both? I’d love to understand where the agent's decision-making ends and the hard rules take over.
NEXA is a modern crypto portfolio dashboard designed to provide a clear overview of digital assets, portfolio performance, market data, and key statistics in one interface.
CryptoScout is a Telegram crypto assistant that provides users with tools for checking wallets and tokens, monitoring portfolios, and accessing useful crypto information directly through Telegram.
Six sit on a bench, each working inside one app a small business already uses. The phone line, Jobber, Gmail, Slack, Teams, QuickBooks. Tap one to hire it or drag it onto the desk.
The desk writes out their Monday hour by hour and adds up the real monthly price. Hit send and the contact form opens with your lineup filled in.
Try it at greenaidigital.com/hire.html
We also just started posting on Instagram, a new AI breakdown every day at noon. instagram.com/greenaidigitals
If you build agents or automations, say hi. Happy to follow back.