"Uncharted Labs team on Alpaca AI Trading Agents Hackathon Hackathon"

Team Idea

Autonomous trading agents have a trust problem: every risk limit is a line of code, and code fails. A stop-loss is an instruction, not a guarantee — it gaps through on a bad open, and it doesn't exist at all if the agent that placed it has a bug. Ashimoto moves the risk limit out of the software and into the instrument. It trades only defined-risk vertical spreads, where maximum loss per position is fixed when the order is constructed and enforced by the broker — not by the agent's control flow. A 3% risk budget stops being a rule the agent has to remember and becomes a property of what it holds. Built on Alpaca's Trading API and CLI.

Team Members

Scott Wilson

Joticle

Principal Software Architect

Submission

Uncharted Options

Autonomous agents ask you to trust that their limits will hold. This one doesn't ask. It trades only defined-risk spreads, where maximum loss is fixed by the broker and the OCC at order construction — not by code that has to remember.