Generative AI in Production
Traditional MLOps is a set of practices to productionize traditional ML systems for enterprise applications. Generative AI raises new challenges in managing and productionizing applications at scale. The field of generative AI operations seeks to address these new challenges. In this course, you learn about the challenges that arise when deploying and productionizing generative AI-powered applications. You learn how to secure your generative AI-powered applications. Finally, you will discuss best practices for logging and monitoring your generative AI-powered applications in production.
- Duration: 1 day
- Languages: English, German
- Level: Advanced
- Group size: Up to 16
What you'll learn
- Understand the challenges in productionizing applications using generative AI
- Manage experimentation and evaluation for LLM-powered application
- Productionize LLM-powered applications
- Secure generative AI applications
- Implement logging and monitoring for LLM-powered applications
Prerequisites
- Completion of the "Application Development with LLMs on Google Cloud" or equivalent knowledge.
Course outline
Introduction to Generative AI in Production
- Generative AI operations
- Traditional MLOps vs. GenAIOps
- Components of an LLM system
- RAG/ReAct architecture
Generative AI Application Deployment
- Application deployment options
- Deployment, packaging, and versioning
Productionizing Generative AI
- Maintenance and updates
- Testing and evaluation
- CI/CD pipelines for gen AI-powered apps
Securing Generative AI Applications
- Security challenges
- Prompt security
- Sensitive Data Protection and DLP API
- Model Armor
Observability for Production LLM Systems
- Cloud Operations
- Cloud Logging
- Monitoring
- Cloud Trace
- Agent Analytics and AgentOps
- Putting it all together
Related courses
Deploy multi-agent systems with Agent Development Kit and Agent Engine
In this course, you’ll learn to use the Google Agent Development Kit to build complex, multi-agent systems. You will build agents equipped with tools, and connect them with parent-child relationships and flows to define how they interact. You’ll run your agents locally and deploy them to Vertex AI Agent Engine to run as a managed agentic flow, with infrastructure decisions and resource scaling handled by Agent Engine.
Vertex Forecasting and Time Series in Practice
This course is an introduction to building forecasting solutions with Google Cloud. You start with sequence models and time series foundations. You then walk through an end-to-end workflow: from data preparation to model development and deployment with Vertex AI. Finally, you learn the lessons and tips from a retail use case and apply the knowledge by building your own forecasting models.
Agent Observability on Google Cloud
This course provides an applied, intermediate guide to operationalizing AI agents, focusing specifically on achieving production confidence and cost predictability for Gemini-powered workflows on Google Cloud. Participants will learn the methodology and actionable skills necessary to transform non-deterministic agent logic into transparent, auditable, and scalable systems.The course covers core operational disciplines, including mapping the agent's complex thought process (ReAct loops) to Cloud Trace Spans for debugging, implementing Logs-Based Security Metrics for compliance, and setting up actionable alerts and custom dashboards in Cloud Monitoring to proactively control cost overruns and quality drift. The course uses presentations, Visual Walkthroughs, and strategic discussions to ensure effective learning that is directly applicable to the Vertex AI ecosystem
Not sure which course fits?
Book a 30-minute call. We'll look at where your team is, what they need to be able to do, and put together either a specific course date or a tailored learning plan.