Skip to main content

Behavioral Intelligence

Recapt's behavioral intelligence is the detection engine that powers self-healing UX. It's a custom ML model (not an LLM) that analyzes every session in real-time to find friction before you know it exists.

The Detection Engine

When a user rage-clicks a button, hesitates on a form, or gets lost in navigation, recapt's behavioral model detects these patterns and flags them as issues. This happens automatically on every session, no manual review required.

The model was trained specifically on user behavior patterns, which gives it capabilities that general-purpose AI lacks:

CapabilityWhat it means
Micro-signal detectionCatches subtle hesitations, tiny scroll adjustments, brief pauses that humans miss in replay
Real-time analysisEvery session is scored as it happens, not in batch
Deterministic outputSame input always produces the same score, no hallucination
Privacy-preservingAnalyzes interaction patterns, not content

What It Detects

Frustration Signals

  • Rage clicks: Rapid, repeated clicks on the same element
  • Dead clicks: Clicks on non-interactive elements
  • Scroll thrashing: Rapid scrolling up and down
  • Backtracking: Repeatedly returning to previous pages
  • Micro-frustrations: Small, rapid scroll reversals or brief repeated clicks that happen too fast to notice in playback

Confusion Signals

  • Hesitation: Long pauses before taking action
  • Erratic movement: Mouse movements that suggest uncertainty
  • Path wandering: Taking indirect routes to complete tasks
  • Form abandonment: Starting but not completing forms
  • Micro-hesitations: Brief pauses and small cursor movements that indicate momentary uncertainty

Engagement Signals

  • Confident navigation: Direct paths to goals
  • Smooth interactions: Steady, purposeful movements
  • Task completion: Successfully finishing intended actions

Behavioral Scores

Every session receives three scores on a 0-1 scale:

ScoreWhat it measuresHigh score means
FrustrationRage clicks, dead clicks, thrashing, backtrackingUser is struggling with the UI
ConfusionHesitation, erratic movement, path wanderingUser doesn't know what to do
ConfidenceDirect navigation, purposeful movementUser is completing tasks smoothly

These scores feed directly into the self-improvement workflow. When frustration spikes on a page, recapt flags it as an issue and the AI investigates.

From Detection to Action

The behavioral model doesn't just report symptoms. It connects signals to causes:

Symptom: "Users are rage-clicking the checkout button"

Cause: "The button appears clickable but doesn't respond until form validation completes"

Fix: "Add a loading state and disable the button until ready"

This causal understanding is what enables autonomous fixing. The AI doesn't just know something is wrong. It knows why, and can propose a specific fix.

Session Outcomes

Beyond scores, recapt automatically classifies each session's outcome:

OutcomeWhat it means
CompletedUser achieved their goal with minimal friction
StruggledUser achieved their goal but with friction
BlockedUser couldn't complete their goal
ExploringUser was browsing without clear intent
DisengagedUser left without meaningful interaction
ErrorUser encountered a technical failure

Learn more: Session Outcomes

Why Not an LLM?

General-purpose LLMs are powerful, but they're not built for this job:

AspectRecapt's Behavioral ModelGeneral-Purpose LLMs
TrainingTrained on real user behavior patternsTrained on text data
OutputConsistent numerical scores (0-1)Generated text that can vary
SpeedReal-time analysis on every sessionSlower, resource-intensive
ReliabilityDeterministic: same input, same outputCan hallucinate or be inconsistent
FocusDetects subtle behavioral signalsOptimized for language understanding

The behavioral model handles detection. LLMs (via the MCP server) handle diagnosis and fixing. Each does what it's best at.

Next Steps