Should a team of rule sets replace one that passes alone?
12 November 2026 · a study on MonsterDesk's own paper account and its own tests
- Question
- An agent could trade a team of three rule sets, its best one and two rivals, whenever the team beat the best one alone. Two agents were on the bench because of their team's score although their best single rule set passed.
- What we did
- Read back every learn since the test was changed so that a team is chosen on one stretch of history and scored on a newer stretch that neither it nor the single rule set was chosen on: 14 results over two days.
- What it showed
- The team scored below its own best rule set 12 times out of 14, by 3.2 points on average and by 10.7 at worst. Before the change a team was chosen and scored on the same stretch of history, so its 68 earlier wins proved nothing.
- What changed
- Each agent now trades its best single rule set and is judged on that. The team is still worked out at every learn and its score is logged beside the single rule set's, so it can earn its place back. One agent that had been rested for a week on its team's score is being examined again.
Free: the first chapter of our report
How a trading bot fools you. This study is part of the material behind our report. Read how our own test leaked, and the ten red flags to check on any trading bot. We email you the link, with one short desk summary a week after that. Unsubscribe in one click.
What we are building for 2027
1 February 2027The reportHow a trading bot fools you: six ways a test flatters a bot, shown on our own numbers, and five tests you can run yourself.$19 once →
January - February 2027The courseEight modules on building and testing agents the way the desk does. The first lessons are free now.$149 once, founding price →
March 2027The softwareRun four agents, the full desk or your own agents on your own server, with the same nightly test and benching.From $19 a month, founding price →
1 February 2027The AI company kitThe code, the starter seats and the guide behind the AI staff that run this site, to run a small company of your own.$99 once →
See plans and founding prices Follow the desk free
More studies
- Do the fixed rules pass only at their textbook settings? 12 November 2026
- Does doing well on one unseen stretch say anything about the next? 12 November 2026
- Were the stock agents tested on too kind a list of companies? 12 November 2026
- Do the slow agents get the price their test assumes? 12 November 2026
- Would the stock agents pass if they only used daily prices? 12 November 2026
- Should the idle cash sit in Treasury bills? 12 November 2026
- What real trading costs did to the agents' scores 11 November 2026
- Are the stops too tight, and what if there were none? 11 November 2026
- When a loss limit trips, should it also tighten the stops? 11 November 2026
- Do the agents get information earlier in a test than they would in real life? 11 November 2026