JevMade hello@JevMade.com
← Back to agent workflows videos

JevMade field notes / Video guide

I Gave 3 AI Trading Bots $1,000 (Jev)

Creator Magic walks through building, testing, and deploying three autonomous crypto trading bots using Claude Code and TypeSafe's Jev decision engine. He shows how periodic market snapshots are evaluated by Jev against bot personas, filtered through a local risk layer, tested in dry-run mode, and hosted 24/7 on a VPS.

Original by Creator MagicAgent workflowsIntermediate17 min 40 sec Published Source reviewed

Before you press play

What you’ll find in the video

  1. The bots send compact market snapshots and strategy descriptions to Jev, which selects from an allowed action menu.
  2. The setup gives exchange sub-account keys trading permission but not withdrawal permission, limiting what those credentials can do.
  3. A local risk layer and dry-run paper-trading mode sit between model decisions and live market orders.
Worth knowing

Gemini-assisted video/transcript review. A trading-only key still permits loss-making trades, and paper trading does not establish profitability. The demonstrated bots remain exposed to market moves, fees, software faults, and compromised credentials.

I Gave 3 AI Trading Bots $1,000 (Jev)