Target Audience
Application Developers, DevOps Engineers, ML Engineers, Anyone deploying agentic applications on Google Cloud
Course Objectives
After this course participants should be able to:
- Navigate the challenges of managing production agents
- Define the core principles of AgentOps
- Architect agent operations on Google Cloud
- Leverage CI/CD tooling and patterns for agentic solutions on Google Cloud
- Select the deployment target for agents on Google Cloud
- Build a complete CI/CD pipeline for an agent
- Identify challenges addressed by observability
- Instrument an ADK agent with structured logs
- Enable OpenTelemetry tracing on Agent Engine and Cloud Run
- Leverage BigQuery and Looker Studio for visualization
- Perform validation on model responses
- Evaluate agent behavior, tool usage, and trajectory correctness
- Create and manage evalsets using ADK Web UI
- Evaluate evalsets with ADK UI, CLI, or code
- Use the Agent Platform Generative AI Evaluation Service
- Secure model inputs and outputs with Model Armor
- Protect sensitive data using Sensitive Data Protection with Model Armor
- Secure the connection between a user and an agent
- Identify the primary cost drivers of AI agents
- Reduce token and model costs
- Architect cost-efficient agent systems
- Implement a measurable AI FinOps loop on Google Cloud
Course Content
01- Introduction to AgentOps on Google Cloud
- Challenges of managing production agents
- Core principles of AgentOps
- AgentOps on Google Cloud
02- CI/CD for Agent Deployments
- CI/CD review
- Agentic deployment targets
- CI/CD tooling and patterns on Google Cloud
- Cloud Build automation
- Activities for Module 2:
- Lab: CI/CD for Agents on Google Cloud
- Lab: CI/CD for Agents on Google Cloud
03- Observability for Debugging and Improvement
- Observability review
- Logging with agent callback logging
- Logging and tracing with OpenTelemetry
- Activities for Module 3:
- Lab: Instrument and Debug Agents with Cloud Logging, and Cloud Trace
04- Agent Evaluation and Quality Assurance
- Testing generative AI model responses
- Evaluating model responses
05- Security and Governance
- Model and context security
- Agent access
06- Applying FinOps to Agent Costs
- Primary cost drivers for AI Agents
- Cost-efficient agentic systems
- FinOps on Google Cloud
Course Prerequisites
- Completion of "Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine" or equivalent knowledge
- Python
- Prompt engineering
- Agent Development Kit
Test Certification
None