Automated Pattern Detection

Continuously analyze your memory store to surface recurring patterns, anomalies, and risks — before they become incidents.

Pattern Types

The Pattern Detector scans memory entries and decision trace data for four pattern types:

Pattern	What it finds	Severity
Recurring failures	Entries that repeatedly appear in incident causal chains	Warning / Critical
Hot entities	Entities with disproportionate write/outcome activity vs. average	Info
Stale clusters	Groups of old entries with no outcome links that may need pruning	Warning
Confidence drift	Entries whose confidence diverges significantly from their entity average	Info

Alert Manager

Configurable rules that fire when matching patterns are detected:

from amfs_patterns import PatternDetector, AlertManager, AlertRule

detector = PatternDetector(incident_threshold=2, stale_days=30)
report = detector.analyze(entries, outcome_data=outcomes)

manager = AlertManager()
manager.add_rule(AlertRule(
    name="Critical recurring failures",
    pattern_type="recurring_failure",
    min_severity="critical",
    cooldown_minutes=60,
))
manager.on_alert(lambda eval: send_slack_notification(eval))

evaluations = manager.evaluate(report)

Features: severity filtering, entity-path scoping, cooldown-based suppression (prevent alert fatigue), and callback registration for routing to Slack, PagerDuty, email, or custom systems.

Product

Getting Started

Guides

Core Concepts

Pro Features

Pattern Detection

Automated Pattern Detection

Pattern Types

Alert Manager

​Automated Pattern Detection

​Pattern Types

​Alert Manager

Automated Pattern Detection

Pattern Types

Alert Manager