Operational Analytics

W33KND

"Your Command Center for the Ecosystem"

A unified stats, tuning, and reporting console designed for the integrated ecosystem of Kairos, Heirloom, and eXitZork. Real-time telemetry, model tuning infrastructure, and therapist-ready clinical reporting.

Explore Console View Landing Page
3 Apps Monitored
HIPAA Aligned
Real-time Telemetry
Ecosystem Coverage

Unified Telemetry

One console to monitor your entire stack.

Kairos

  • Router decision tracking
  • Model performance metrics
  • Latency monitoring
  • Refusal analysis

Heirloom

  • Wellness session tracking
  • Mood trend analysis
  • User check-in rates
  • Therapist reporting

eXitZork

  • Gameplay progression
  • Assessment signal capture
  • Cognitive pattern analytics
  • Session health tracking
Core Features

Complete Observability Suite

Everything you need to monitor, tune, and report on your ecosystem.

Data Plane

Ingestion API (/w33knd/v1/events) with Postgres, ClickHouse, and Redis storage for high-throughput event processing.

Control Plane

Registries for models, prompts, policies, and experiment definitions. A/B testing infrastructure built-in.

Presentation Plane

Engineering Console for developers and Clinician Dashboards for healthcare professionals.

Interactive Visualizations

Dark-themed Matplotlib charts for multi-series trends, heatmaps, and performance gauges.

Export Utilities

Automated report generation in JSON, CSV, HTML, and Markdown formats for clinical research.

Governance

HIPAA-aligned de-identification and AI risk management following NIST AI RMF guidelines.

Clinical Portal

Therapist Command Center

A fully implemented clinical portal integrating EHR-like functionalities with real-time telemetry.

Outcome Tracking

PHQ-9 and GAD-7 visualization with severity mapping

Unified Roster

Client list with risk status and engagement metrics

Clinical Alerts

Severity-based warnings for mood spikes or drops

WHO-5 Integration

Wellbeing research with behavioral phenotyping

Therapist Portal
JD
Patient #1247 Stable
PHQ-9: 4
SM
Patient #1248 Monitor
PHQ-9: 12
AK
Patient #1249 Improving
PHQ-9: 6
Technical Stack

Built for Scale

A modular CustomTkinter desktop application with panel-based architecture.

Python + CustomTkinter

Modern desktop GUI framework

Postgres + ClickHouse + Redis

Multi-layer storage architecture

Docker-Native Orchestration

Container-ready deployment

TypeScript SDK

Native ecosystem integration

analytics_engine.py 
class AnalyticsEngine:
    """Real-time processing and reporting."""

    def process_event(self, event: Event):
        # Time-series analysis
        self.time_series.append(event)

        # Anomaly detection
        if self.detect_anomaly(event):
            self.alert_clinician(event)

        # Report generation
        self.reports.generate(
            format=['json', 'csv', 'html']
        )
Roadmap

What's Next

Upcoming features and improvements.

LLM Observability

Enhanced tracking specifications for language model operations.

Master Account Service

Unified authentication and data aggregation across all products.

Deep Insights & Continuous Improvement

High-fidelity tracking points and improvement logging.

Behavioral Phenotyping Pipelines

Passive biomarker correlation validation.

Take Control of Your Ecosystem

W33KND gives you complete visibility into your applications.

View Landing Page Get in Touch Explore Other Products