Tag
The author explains how to build a 24/7 AI financial trading agent using a combination of Minara and Jev, claiming to have turned 100U of capital into a 174% return in 7 days, and shares a complete workflow covering data acquisition, decision-making, backtesting, risk control, and execution.
The author gave a talk at Google on AI Agent Harness Engineering, demonstrating a Financial Agent using Gemma 4 local LLMs that ran under 15 GB RAM and performed on par with frontier models.