Manage model monitor | Gemini Enterprise Agent Platform | Google Cloud Documentation

Skip to main content

Documentation

Get Started

Get Started with Google Cloud
Product List
Cloud Customer Care

Featured Products

Agent Platform
Apigee API Management
BigQuery
Compute Engine
Cloud CDN
Cloud Run
Cloud Storage
Cloud SQL
Gemini Enterprise
Google Kubernetes Engine
Looker

Cross-product Tools

Access and resources management
Costs and usage management
Infrastructure as code
SDK, languages, frameworks, and tools

Technology Areas

AI and ML
Application development
Application hosting
Compute
Data analytics and pipelines
Databases
Distributed, hybrid, and multicloud
Industry solutions
Migration
Networking
Observability and monitoring
Security
Storage

/

Console

English
Deutsch
Español – América Latina
Français
Indonesia
Italiano
Português – Brasil
עברית
中文 – 简体
中文 – 繁體
日本語
한국어

Sign in

Gemini Enterprise Agent Platform

Start free

Overview Studio Agents Models Notebooks

Agent Platform
Generative AI

Engineering Blog

Documentation
- More
- Overview
- Studio
- Agents
- Models
- Notebooks
- Pricing
  - More
- Engineering Blog
Console

Overview
Beginner's guide
Get started
Get started with Agent Platform
Develop Gemini API code with the Gen AI SDK
Connect to the Knowledge MCP server
Get an API key
Configure application default credentials
Migrate from Google AI Studio to Agent Platform
Get started with Gemini 3
Developer guides for Gemini models
Google GenAI libraries
Generative AI cookbook
Access Gemini models using OpenAI libraries
Express mode
Select models
- Model Garden
- Overview of Model Garden
- Use models in Model Garden
- Test model capabilities
- Google Models
- All Google models
- Gemini
  - Migrate to the latest Gemini models
  - Pro
  - 3.1 Pro
  - 3 Pro Image
  - 2.5 Pro
  - Flash
  - Gemini Omni 1.1 Flash
  - Gemini Omni Flash
  - 3.8 Flash
  - 3.7 Flash
  - 3.6 Flash
  - 3.5 Flash
  - 3.1 Flash Image
  - 3 Flash
  - 2.5 Flash
  - 2.5 Flash Image
  - 2.5 Flash Live API
  - Flash-Lite
  - 3.5 Flash-Lite
  - 3.1 Flash-Lite Image
  - 3.1 Flash-Lite
  - 2.5 Flash-Lite
  - Transcribe
  - Gemini 3.5 Transcribe
  - Translate
  - Gemini 3.5 Live Translate
  - Embedding
  - Gemini Embedding 2
  - Robotics
  - Gemini Robotics ER 2
    Overview
    Spatial reasoning
    Agentic capabilities
    Task orchestration
    Video understanding
- Veo
  - Veo 3
  - Veo 3.1
- Lyria
  - Lyria 2
  - Lyria 3
- Virtual Try-On
- Model versions
- Partner Models
- Partner models overview
- Claude
- Grok
  - Overview
  - Responses API
  - Function calling
  - Structured output
  - Reasoning
  - Model details
  - Grok 4.1 Fast
  - Grok 4.20
  - Grok 4.3
  - Grok 4.6
- Mistral AI
  - Overview
  - Model details
  - Mistral Medium 3
  - Mistral OCR (25.05)
  - Mistral Small 3.1 (25.03)
  - Codestral 2
- Deploy partner models from Model Garden
- Partner model deprecations
- Open Models
- Overview
- AlphaFold 3
- AlphaGenome
- DeepSeek
- Embedding (e5)
  - Multilingual E5 Small
  - Multilingual E5 Large
- Google Gemma
- Kimi
  - Overview
  - Kimi K2 Thinking
- Llama
  - Overview
  - Request predictions
  - Model details
  - Llama 4 Maverick
  - Llama 4 Scout
  - Llama 3.3
- MiniMax
  - Overview
  - MiniMax M2
- OpenAI
- Qwen
- ZAI.org
- Managed open models (MaaS)
- Self-deployed open models
Build
- Prompt design
- Introduction to prompting
- Prompting strategies
- Task-specific prompt guidance
  - Design multimodal prompts
  - Design chat prompts
- Capabilities
- Safety
- Text and code generation
- Image generation
- Video generation
- Music generation
- Media analysis
- URL context
- Thinking
- Live API
- Embeddings
  - Overview
  - Text embeddings
    Get text embeddings
    Choose an embeddings task type
  - Get multimodal embeddings
  - Get batch embeddings inferences
- Translation
- Generate speech from text
- Transcribe speech
- Model tools
- Code execution
- Computer use
- Function calling
- Grounding
- Development tools
- Use AI-powered prompt writing tools
  - Overview
  - Optimize prompts
    Overview
    Zero-shot optimizer
    Few-shot optimizer
    Data-driven optimizer
  - Use prompt templates
- Model tuning
- Introduction to tuning
- Tuning Gemini models
  - Supervised fine-tuning
    About supervised fine-tuning
    Prepare your data
    Use supervised fine-tuning
    
    Supported modalities
    Text tuning
    Document tuning
    Image tuning
    Audio tuning
    Video tuning
    Tune function calling
  - Reinforcement learning fine-tuning
    About reinforcement learning fine-tuning
    Quick start
    
    Reinforcement learning fine-tuning job
    Overview
    Tuning dataset
    Hyperparameters
    Reward functions
    Metrics and monitoring
    Continuous tuning
  - Preference tuning
    About preference tuning
    Prepare your data
    Use preference tuning
  - Use tuning checkpoints
  - Use continuous tuning
  - Tuning recommendations with LoRA and QLoRA
- Open models
  - Supervised and distillation fine-tuning
- Embeddings models
  - Tune text embeddings models
- Translation models
- Migrate
- Call Agent Platform models using OpenAI libraries
Evaluate
- Overview
- Tutorial: Perform evaluation using the console
- Perform evaluation using the GenAI Client in Agent Platform SDK
- Alternative evaluation methods
- Evaluate using the evaluation module in Agent Platform SDK
- Run AutoSxS pipeline
- Run a computation-based evaluation pipeline
Deploy
Administer
Build your own model
- Overview
- MLOps on Agent Platform
- Interfaces for Agent Platform
- Agent Platform beginner's guides
  - Train an AutoML model
  - Train a custom model
  - Get inferences from a custom model
  - Train a model using Agent Platform and the Python SDK
    Introduction
    Prerequisites
    Create a notebook
    Create a dataset
    Create a training script
    Train a model
    Make an inference
- Integrated ML frameworks
  - PyTorch
  - TensorFlow
- Agent Platform for BigQuery users
- Glossary
- Get started
- Set up a project and a development environment
- Install the Agent Platform SDK for Python
- Authenticate to Agent Platform
- Choose a training method
- Try a tutorial
  - Tutorials overview
  - AutoML tutorials
    
    Hello image data
    Overview
    Set up your project and environment
    Create a dataset and import images
    Train an AutoML image classification model
    Evaluate and analyze model performance
    Deploy a model to an endpoint and make an inference
    Clean up your project
    
    Hello tabular data
    Overview
    Set up your project and environment
    Create a dataset and train an AutoML classification model
    Deploy a model and request an inference
    Clean up your project
  - Custom training tutorials
    Train a custom tabular model
    
    Train a TensorFlow Keras image classification model
    Overview
    Set up your project and environment
    Train a custom image classification model
    Serve predictions from a custom image classification model
    Clean up your project
    Fine-tune an image classification model with custom data
- Use Agent Platform development tools
- Development tools overview
- Use the Agent Platform SDK
  - Overview
  - Introduction to the Agent Platform SDK for Python
  - Agent Platform SDK for Python classes
    Agent Platform SDK classes overview
    Data classes
    Training classes
    Model classes
    Prediction classes
    Tracking classes
- Terraform support for Agent Platform
- Agent Platform Training
- Overview
- Agent Platform serverless training
  - Overview of serverless training in Agent Platform
  - Load and prepare data
    Data preparation overview
    Use Cloud Storage as a mounted file system
    Mount an NFS share for serverless training
    Use managed datasets
  - Prepare training application
    Understand the serverless training service
    Prepare training code
    
    Use prebuilt containers
    Create a Python training application for a prebuilt container
    Prebuilt containers for serverless training
    
    Use custom containers
    Custom containers for serverless training
    Create a custom container
    Containerize and run training code locally
  - Train on a persistent resource
    Overview
    Create persistent resource
    Run training jobs on a persistent resource
    Get persistent resource information
    Reboot a persistent resource
    Delete a persistent resource
  - Configure training job
    Choose a custom training method
    Configure container settings for training
    Configure compute resources for training
    Use reservations with training
    Use Spot VMs with training
  - Submit training job
    Create custom jobs
    
    Hyperparameter tuning
    Hyperparameter tuning overview
    Use hyperparameter tuning
    Create training pipelines
    Schedule jobs based on resource availability
    Use distributed training
    Training with Cloud TPU VMs
    Use private IP for custom training
    Use Private Service Connect interface for training (recommended)
  - Monitor and debug
    Monitor and debug training using an interactive shell
    Profile model training performance
  - Tutorial: Build a pipeline for continuous training
  - Create custom organization policy constraints
- Gemini Enterprise Agent Platform clusters
  - Overview
  - Get started with training clusters
  - Deployment considerations
    Compute resources
    Networking
    Storage
    Orchestration
  - Create and manage clusters
    Create cluster
    View clusters
    Manage cluster
    Manage accounts and job scheduling on a cluster
  - Cluster resiliency
  - Monitor resilience events with a dashboard
  - Feature guides
    Using Flex Start VMs with Slurm clusters
  - Run workload on cluster
    Run prebuilt workloads
    Visualizing jobs with TensorBoard
    Manage training clusters using Slurm
- Ray on Agent Platform
- Perform Neural Architecture Search
- Optimize using Agent Platform Vizier
  - Overview of Agent Platform Vizier
  - Create Agent Platform Vizier studies
- AutoML model development
  - AutoML training overview
  - Image data
    
    Classification
    Prepare data
    Create dataset
    Train model
    Evaluate model
    Get predictions
    Interpret results
    
    Object detection
    Prepare data
    Create dataset
    Train model
    Evaluate model
    Get predictions
    Interpret results
    Encode image data using Base64
    Export an AutoML Edge model
  - Tabular data
    Overview
    Introduction to tabular data
    
    Tabular Workflows
    Overview
    
    End-to-End AutoML
    Overview
    Train a model
    Get online inferences
    Get batch inferences
    
    Forecasting
    Overview
    Train a model
    Get online inferences
    Get batch inferences
    Pricing
    Service accounts
    Manage quotas
    
    Perform classification and regression with AutoML
    Overview
    Quickstart: AutoML Classification (Cloud Console)
    Prepare training data
    Create a dataset
    Train a model
    Evaluate model
    View model architecture
    Get online inferences
    Get batch inferences
    Export model
    
    Perform forecasting with AutoML
    Overview
    Prepare training data
    Create a dataset
    Train a model
    Evaluate model
    Get inferences
    Hierarchical forecasting
    Perform forecasting with ARIMA+
    Perform forecasting with Prophet
    Perform entity reconciliation
    Feature attributions for classification and regression
    Feature attributions for forecasting
    Data types and transformations for tabular AutoML data
    Training parameters for forecasting
    Data splits for tabular data
    Best practices for creating tabular training data
  - Train an AutoML Edge model
    Using the Console
    Using the API
- Generative AI model development
- Overview
- Create and manage datasets
- Overview
- Data splits for AutoML models
- Create an annotation set
- Delete an annotation set
- Add labels (console)
- Export metadata and annotations from a dataset
- Manage image dataset versions (API only)
- Get inferences
- Overview
- Configure models for inference
- Get online inferences
- Get batch inferences
- Serve generative AI models
- Custom organization policies
- Machine learning operations (MLOps)
- Manage features
  - Feature management in Agent Platform
  - Agent Platform Feature Store
    About Agent Platform Feature Store
    
    Set up features
    Prepare data source
    Create a feature group
    Create a feature
    
    Set up online serving
    Online serving types
    Create an online store instance
    Create a feature view instance
    
    Control access
    Control access to resources
    
    Sync online store
    Start a data sync
    List sync operations
    Update features in a feature view
    
    Serve features
    Serve features from online store
    Serve historical feature values
    
    Monitor
    Monitor features
    
    Manage feature resources
    List feature groups
    List features
    Update a feature group
    Update a feature
    Delete a feature group
    Delete a feature
    
    Manage online store resources
    List online stores
    List feature views
    Update an online store
    Update a feature view
    Delete an online store
    Delete a feature view
    
    Feature metadata
    Update labels
    
    Search for resources
    Search for resources
    Search for resource metadata in Data Catalog
    
    Manage embeddings
    Search using embeddings
    
    Notebook tutorials
    Agent Platform Feature Store tutorial notebooks
- Manage models
- Evaluate models
  - Model evaluation in Agent Platform
  - Perform model evaluation in Agent Platform
  - Model evaluation for fairness
    Introduction to model evaluation for fairness
    Data bias metrics for Agent Platform
    Model bias metrics for Agent Platform
- Orchestrate ML workflows using pipelines
  - Introduction
  - Interfaces
  - Configure your project
  - Build a pipeline
  - Run a pipeline
  - Use pipeline templates
    Create, upload, and use a pipeline template
    Use a prebuilt template from the Template Gallery
  - Configure your pipeline
    Configure execution caching
    Configure failure policy
    Configure retries for a pipeline task
    Specify machine types for a pipeline step
    Request Google Cloud machine resources with Agent Platform Pipelines
    Configure Private Service Connect interface (recommended)
    Configure secrets with Secret Manager
    Configure a pipeline run on a persistent resource
  - Schedule and trigger pipeline runs
    Schedule a pipeline run with scheduler API
    Trigger a pipeline run with Pub/Sub
  - Cancel or delete pipeline runs
    Cancel pipeline runs
    Delete pipeline runs
  - Rerun a pipeline
  - Monitor pipeline execution
    View pipeline metrics
    View pipeline job logs
    Route logs to a Cloud Pub/Sub sink
    Configure email notifications
  - Visualize results
    Visualize and analyze pipeline results
    Track the lineage of pipeline artifacts
    Output HTML and Markdown
  - Resource labeling by Agent Platform Pipelines
  - Understand pipeline run costs
  - Migrate from Kubeflow Pipelines to Agent Platform Pipelines
  - Use custom constraints
  - Google Cloud Pipeline Components
    Quickstart
    Introduction to Google Cloud Pipeline Components
    Google Cloud Pipeline Component list
    Use Google Cloud Pipeline Components
    Build your own pipeline components
  - Agent Platform Pipelines tutorials
    Tutorial notebooks
- Track and analyze your ML metadata
- Monitor model quality
  - Introduction to Model Monitoring
  - Model Monitoring v2
    Set up model monitoring
    Run monitoring jobs
    Manage model monitors
  - Model Monitoring v1
    Provide schemas to Model Monitoring
    Monitor feature skew and drift
    Model Monitoring for batch predictions
- Track Experiments
- Administer
- Access control
- Monitor Agent Platform resources
  - Cloud Monitoring metrics
  - Audit logging information
- Networking
- Security
- Name resources
- Samples and tutorials
- Notebook tutorials
- Code samples
  - Code samples for all products

Get Started
Get Started with Google Cloud
Product List
Cloud Customer Care
Featured Products
Agent Platform
Apigee API Management
BigQuery
Compute Engine
Cloud CDN
Cloud Run
Cloud Storage
Cloud SQL
Gemini Enterprise
Google Kubernetes Engine
Looker
Cross-product Tools
Access and resources management
Costs and usage management
Infrastructure as code