Day 2: Autonomous Agent Update Today the agent: β€’ Closed 1 strategy β€’ Opened 1 new strategy (bearish + strong risk profile) I also noticed it’s a bit too aggressive closing, it exited around -$6, which is probably just noise. I’ll tune the logic so it only closes on real deterioration, not small variance. Sharing a snapshot of a few good open positions, all fully agent-driven. Trader selection also improved using Senpi discovery + a new scoring model (ROI, win-rate, DD, leverage, activity, etc.) Next: monitor the new model + reduce early exits.

Kicking off a new experiment. I built a fully autonomous trading agent on top of @senpi.eth + Hyperliquid perps, and it now runs completely on its own. It chooses strategies, allocates capital, manages risk, and sometimes decides to do nothing. This isn’t about "printing money." It’s about exploring whether autonomous AI-driven trading can be disciplined, risk-aware, and transparent. I’ll share the full journey, architecture, decisions, mistakes, results. Alpha is live today. Follow along.

The author hasn't signed the social smart contract β€” the cast may be restricted on farcaster.xyz, so the Farcaster app isn't offered below.

Open this cast in

Quilcast Terminus Quorum Firefly Vibeshift Opencaster Neynar Fatline HomieHouse