Agent Observability on Google Cloud
Module 00: Course Introduction
Full name: Agent Observability on Google Cloud
Product code: T-AGTOBS (Cloud Sparks)
These links are based on the current course version.
Module 01: The Google Cloud Observability Foundation
Websites
- Cloud Trace overview https://cloud.google.com/trace/docs/overview
- Cloud Logging documentation https://cloud.google.com/logging/docs
- Cloud Monitoring documentation https://cloud.google.com/monitoring/docs
- OpenTelemetry on Google Cloud https://cloud.google.com/trace/docs/setup#opentelemetry
- Vertex AI Agent Engine https://cloud.google.com/vertex-ai/docs/agents/agent-engine
- Cloud Audit Logs https://cloud.google.com/logging/docs/audit
- Logs-based metrics https://cloud.google.com/logging/docs/logs-based-metrics
- Custom dashboards in Cloud Monitoring https://cloud.google.com/monitoring/dashboards
- Alerting policies https://cloud.google.com/monitoring/alerts
- VPC Service Controls https://cloud.google.com/vpc-service-controls/docs/overview
- Sensitive Data Protection (DLP) https://cloud.google.com/sensitive-data-protection/docs
Videos
- Cloud logging https://www.youtube.com/watch?v=gyDp-Cl_MdA
- Distributed tracing with OpenTelemetry and Cloud Trace https://www.youtube.com/watch?v=NQeK8Kbu6UM
- Create Alerts on Cloud Monitoring https://www.youtube.com/watch?v=D0YKWvuJgwg
- Introduction to Vertex AI Agent Engine https://www.youtube.com/watch?v=NrgoZLcY3Kk
- Protect your resources with VPC Service Controls https://www.youtube.com/watch?v=TD06WkY1zLs
Module 02: Proactive Monitoring and Evaluation
Websites
- Service Level Objectives (SLOs) https://cloud.google.com/stackdriver/docs/solutions/slo-monitoring
- Custom metrics overview https://cloud.google.com/monitoring/custom-metrics
- Log sinks (routing and export) https://cloud.google.com/logging/docs/export
- Vertex AI Evaluation https://cloud.google.com/vertex-ai/generative-ai/docs/models/evaluation-overview
- Groundedness evaluation https://cloud.google.com/vertex-ai/generative-ai/docs/models/determine-eval
Videos
- Debugging, distributed tracing, and profiling for web applications https://www.youtube.com/watch?v=CjGv1bDy9rI
Module 03: Tools for Governance & Scaling
Websites
- Google Cloud Operations Suite https://cloud.google.com/products/operations
- Cloud Run deployment options https://cloud.google.com/run/docs
- Agent Engine vs Cloud Run comparison https://cloud.google.com/vertex-ai/docs/agents/agent-engine
- Cloud Billing budgets and alerts https://cloud.google.com/billing/docs/how-to/budgets
- Data governance in the AI era https://cloud.google.com/blog/products/data-analytics/data-governance-in-the-age-of-generative-ai