Discussing the article: "Architecture for Collective Trading Decisions by AI Agents"

New comment
 

Check out the new article: Architecture for Collective Trading Decisions by AI Agents.

The article describes the architecture of a multi-agent trading system based on the grok-4-fast language model, in which, instead of a single system prompt, four independent analysts with fundamentally different roles operate: a bull, a bear, a risk manager, and an arbiter. Three analysts run in parallel using a ThreadPoolExecutor and, within 3–5 seconds, formulate well-reasoned positions based on the same market data; after that, a deterministic judge renders a final verdict according to strict rules.

When a trader looks at a chart and makes a decision, they never do so alone, even if there’s no one else in the room. Several voices speak at once in their head. One notes that the price has broken through the moving average from below and that momentum is positive. Another objects: the RSI is already at 68, the stochastic is in overbought territory, and the latest candle has a long upper shadow—someone is actively selling at these levels. The third one does not mention direction at all and says only this: ATR is three times higher than normal today; it is a news day, and any position right now is a gamble.

A professional trader knows how to listen to all three voices at the same time and weigh them against one another. A beginner hears only the first one—and loses money on what seemed obvious.

When we connect a large language model to MetaTrader 5—which was the focus of the previous article in this series, where we described the Shtenco AI V17 architecture with a WebSocket server and the PRICES command—we are essentially replacing that entire internal dialogue with a single voice. The model receives data, processes it using its single system prompt, and returns a response. The answer may be right, it may be wrong, but it is always just one answer—without doubt, without contradiction, without weighing the alternatives. That is the problem—not a technical one, but an architectural one.

A language model that operates with a single system prompt such as “You are a professional trader; give clear signals” will inevitably tend to generate signals. It is optimized for the task it has been assigned. If it is told, “give me buy or sell,” it will return buy or sell—even when the market is screaming, “Stop, this is not your moment.” A neutral hold in this configuration is always a losing proposition for a model that is trying to be useful.


Author: Yevgeniy Koshtenko

New comment