{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f4d1c7fa63dc4f2ab92dbc6740c54f50\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f4d1c7fa63dc4f2ab92dbc6740c54f50-7925e612e721b777.gif","duration":172.367,"title":"Trusted Unattended Automation for Real Money","description":"This Loom explains the approach Will takes to building trusted unattended automation, using his automated trading bot as the hardest example. The system pulls news from Twitter, the Financial Times, Reuters, Google News, earnings, and the calendar, scores sentiment with AI, and uses cheaper models for routine items while reserving more expensive models for tricky cases. His bot watches 200 assets but trades about 20, connects news to held funds, and adjusts them automatically within a strict risk framework before any order is placed. It performs dry-run execution gating to ensure no assets pass without meeting parameters, logs every decision for auditing, and has run 14 tests."}