Загрузка...

LLM Governance Monitor | Datadog Challenge - AI Partner Catalyst Hackathon

LLM Observability | AI Governance | Datadog | Google Cloud Vertex AI | Prompt Injection Detection | Real-time Monitoring

LLM Governance Monitor is an active, self-healing observability solution for Large Language Model applications. Instead of just watching problems happen, it actively prevents them — detecting threats, making decisions, and protecting LLM infrastructure autonomously.

LINKS
- Live App: https://llm-governance-monitor-852577507346.us-central1.run.app
- GitHub: https://github.com/louizabou/llm-governance-monitor

KEY FEATURES
- Active Governance Engine with automatic threat blocking
- Real-time metrics: latency, tokens, cost, safety, health score
- Self-healing architecture with STRICT MODE escalation
- Datadog integration: dashboard, 5 monitors, anomaly detection ML
- Cost optimization: blocked requests save API costs

TECH STACK
- Google Cloud Vertex AI (Gemini 2.0 Flash)
- Datadog APM, Metrics, Events
- FastAPI, Python, Cloud Run

Built by Louiza Boujida for AI Partner Catalyst Hackathon 2025 (Datadog Challenge)

Видео LLM Governance Monitor | Datadog Challenge - AI Partner Catalyst Hackathon канала louiza boujida
Яндекс.Метрика
Все заметки Новая заметка Страницу в заметки
Страницу в закладки Мои закладки
На информационно-развлекательном портале SALDA.WS применяются cookie-файлы. Нажимая кнопку Принять, вы подтверждаете свое согласие на их использование.
О CookiesНапомнить позжеПринять