Skip to main content
Behavioral detection is a core part of Engram’s design – embedded into how the agent communicates, not bolted on as a standalone feature. Five patterns are monitored through a combination of trade history, decision patterns, and conversational cues. The detectors activate progressively as a trader’s lesson history accumulates enough signal for the agent to distinguish behavior from noise.

​
Detected Patterns

​
Tilt Detection

Revenge trading or emotional escalation after losses. The agent watches for increasing position sizes, shortening hold times, or setup criteria being ignored following a losing trade. When the pattern surfaces, the agent adjusts its communication — recommending a pause, reducing proposed position sizes, or flagging the behavior explicitly.

​
FOMO Detection

Urgency-driven entries without structural justification. When a trader pushes to enter a rapidly moving market without the agent identifying a valid setup, the mismatch is flagged. The agent distinguishes between legitimate momentum trades (supported by data) and emotional chasing (driven by fear of missing out).

​
Overconfidence Detection

Position sizing that exceeds conviction level. When a trader consistently overrides sizing recommendations upward, or concentrates risk beyond what setup quality justifies, the pattern surfaces and the agent responds with more detailed risk framing on subsequent proposals.

​
Anchoring Bias

Fixation on specific price levels without structural basis. When a trader’s reasoning repeatedly returns to a price that isn’t supported by volume profile, liquidation clusters, or other structural data, the agent flags the anchor and offers alternative reference points.

​
Recency Bias

Recent outcomes weighted disproportionately in current decisions. A string of wins leading to oversized positions, or a string of losses leading to hesitation on valid setups — both patterns surface through the agent’s analysis.

​
Why This Matters

Most trading platforms optimize for activity — more trades, more engagement. Engram’s psychology layer does the opposite: it actively discourages bad trades. The network’s value compounds from lesson quality, not trade volume. A trader who trades less but trades well produces more valuable lessons than one who trades constantly but poorly.