Agent Operations on Google Cloud

Agent Operations on Google CloudAOPGCGOGoogleGO-AOPGC1.0<ul> <li>Optimize efficiency and consistency of agent deployments with CI/CD</li><li>Ensure agent quality by implementing and operating evaluation systems</li><li>Leverage observability solutions for debugging and continuous improvement</li><li>Establish guardrails against agent-specific threats</li><li>Build and use a governed artifact management ecosystem</li><li>Apply FinOps strategies to understand and manage agent costs</li></ul><ul> <li>Completion of <a class="fl-href-prod" href="/swisscom/fr/course/google-dmasadkae"><svg role="img" aria-hidden="true" focusable="false" data-nosnippet class="cms-linkmark"><use xlink:href="/css/img/icnset-linkmarks.svg#linkmark"></use></svg>Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine (DMASADKAE)</a> or equivalent knowledge</li><li>Python</li><li>Prompt engineering</li><li>Agent Development Kit</li></ul>Application Developers, DevOps Engineers, ML Engineers and anyone deploying agentic applications on Google Cloud<h4>Module 1 - Introduction to AgentOps on Google Cloud</h4> Topics: <ul> <li>Challenges of managing production agents</li><li>Core principles of AgentOps</li><li>AgentOps on Google Cloud</li></ul>Objectives: <ul> <li>Navigate the challenges of managing production agents</li><li>Define the core principles of AgentOps</li><li>Architect agent operations on Google Cloud</li></ul><h4>Module 2 - CI/CD for Agent Deployments</h4> Topics: <ul> <li>CI/CD review</li><li>Agentic deployment targets</li><li>CI/CD tooling and patterns on Google Cloud</li><li>Cloud Build automation</li></ul>Objectives: <ul> <li>Leverage CI/CD tooling and patterns for agentic solutions on Google Cloud</li><li>Select the deployment target for agents on Google Cloud</li><li>Build a complete CI/CD pipeline for an agent</li></ul>Activities: <ul> <li>Lab: CI/CD for Agents on Google Cloud</li></ul><h4>Module 3 - Observability for Debugging and Improvement</h4> Topics: <ul> <li>Observability review</li><li>Logging with agent callback logging</li><li>Logging and tracing with OpenTelemetry</li></ul>Objectives: <ul> <li>Identify challenges addressed by observability</li><li>Instrument an ADK agent with structured logs</li><li>Enable OpenTelemetry tracing on Agent Engine and Cloud Run</li><li>Leverage BigQuery and Looker Studio for visualization</li></ul>Activities: <ul> <li>Lab: Instrument and Debug Agents with Cloud Logging, and Cloud Trace</li></ul><h4>Module 4 - Agent Evaluation and Quality Assurance</h4> Topics: <ul> <li>Testing generative AI model responses</li><li>Evaluating model responses</li></ul>Objectives: <ul> <li>Perform validation on model responses</li><li>Evaluate agent behavior, tool usage, and trajectory correctness</li><li>Create and manage evalsets using ADK Web UI</li><li>Evaluate evalsets with ADK UI, CLI, or code</li><li>Use the Vertex AI Generative AI Evaluation Service</li></ul>Activities: <ul> <li>Lab: Evaluating Agents with ADK</li></ul><h4>Module 5 - Security and Governance</h4> Topics: <ul> <li>Model and context security</li><li>Agent access</li></ul>Objectives: <ul> <li>Secure model inputs and outputs with Model Armor</li><li>Protect sensitive data using Sensitive Data Protection with Model Armor</li><li>Secure the connection between a user and an agent</li></ul>Activities: <ul> <li>Lab: Enhancing AI Security with Model Armor and Sensitive Data Protection</li></ul><h4>Module 6 - Applying FinOps to Agent Costs</h4> Topics: <ul> <li>Primary cost drivers for AI Agents</li><li>Cost-efficienct agentic systems</li><li>FinOps on Google Cloud</li></ul>Objectives: <ul> <li>Identify the primary cost drivers of AI agents</li><li>Reduce token and model costs</li><li>Architect cost-efficient agent systems</li><li>Implement a measurable AI FinOps loop on Google Cloud</li></ul>- Optimize efficiency and consistency of agent deployments with CI/CD - Ensure agent quality by implementing and operating evaluation systems - Leverage observability solutions for debugging and continuous improvement - Establish guardrails against agent-specific threats - Build and use a governed artifact management ecosystem - Apply FinOps strategies to understand and manage agent costs- Completion of Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine (DMASADKAE) or equivalent knowledge - Python - Prompt engineering - Agent Development KitApplication Developers, DevOps Engineers, ML Engineers and anyone deploying agentic applications on Google CloudModule 1 - Introduction to AgentOps on Google Cloud Topics: - Challenges of managing production agents - Core principles of AgentOps - AgentOps on Google Cloud Objectives: - Navigate the challenges of managing production agents - Define the core principles of AgentOps - Architect agent operations on Google Cloud Module 2 - CI/CD for Agent Deployments Topics: - CI/CD review - Agentic deployment targets - CI/CD tooling and patterns on Google Cloud - Cloud Build automation Objectives: - 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 Activities: - Lab: CI/CD for Agents on Google Cloud Module 3 - Observability for Debugging and Improvement Topics: - Observability review - Logging with agent callback logging - Logging and tracing with OpenTelemetry Objectives: - 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 Activities: - Lab: Instrument and Debug Agents with Cloud Logging, and Cloud Trace Module 4 - Agent Evaluation and Quality Assurance Topics: - Testing generative AI model responses - Evaluating model responses Objectives: - 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 Vertex AI Generative AI Evaluation Service Activities: - Lab: Evaluating Agents with ADK Module 5 - Security and Governance Topics: - Model and context security - Agent access Objectives: - 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 Activities: - Lab: Enhancing AI Security with Model Armor and Sensitive Data Protection Module 6 - Applying FinOps to Agent Costs Topics: - Primary cost drivers for AI Agents - Cost-efficienct agentic systems - FinOps on Google Cloud Objectives: - 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 Cloud1 jour595.00820.00550.00650.00550.00550.00550.00550.00