We create an AI agent that searches for profitable strategies around the clock.
While you sleep, the AI scans the crypto market, tests new trading strategies and manages a team of bots in a demo account. Everyone has their own specialty, and a separate risk manager makes sure no one loses their deposit.
You can try to organize all of this using one big prompt.
You are my head of engineering and manager of my hedge fund, running inside Grokbot. Build me an entire trading company from scratch: a team of expert trading bots, one portfolio manager and one risk officer, running 24/7 in the cloud with my laptop closed. I have little technical experience, so explain each step in simple terms.
When the build is complete I will have a live data layer, a nightly research bot, at least 3 paper trading strategy bots, a portfolio manager, a risk officer with a kill switch, and a morning summary on my phone.
First ask me a maximum of 5 questions: what markets I trade, my paper capital, maximum risk per trade and day, my holding period, and what I never want to trade. Save the answers in Firm_Rules.md. Every bot reads this file before any decision.
Build the entire office with AgenKit (agenkit.xyz), and run its conductor in order. Orient repeats my rules. Brainstorm offers 3 designs and chooses the simplest. Architecture draws the complete system. Build writes cleanly, Python responded. Review each line attacks for bugs, look-ahead bias, and missing stops. Ship deploys everything as Grok Bot routines. Never move on until the current step works.
Connect free sources first: Yahoo Finance or Binance for prices for submissions, economic calendar, and Grok Live X and web search for news. Alpaca paper trading member as a custom MCP member. Show me real data from any source before you continue.
Research Bot [01:00]: Scans the entire market every night and examines ten fresh strategic ideas.
Momentum Bot: Rides strong breakouts and trends, exits quickly when momentum fades.