Learn how to build and deploy AI solutions with H2O.ai’s suite of tools. This course introduces you to key platforms like Driverless AI,H2O Actions, Wave App, GenAI AppStore, LLM DataStudio, H2O LLMStudio, Enterprise GPTe, h2oGPT, and Eval Studio.
You will also gain hands-on experience preparing and visualizing data, automating machine learning workflows, deploying models, and applying generative AI capabilities for advanced tasks such as text generation and translation.
By the end, you’ll be able to navigate H2O.ai’s platforms and apply AI solutions across various industries and use cases.
What you'll learn
Data Preparation and Visualization Learn how to clean, transform, and explore data using H2O’s intuitive tools for efficient analysis.
Automated Machine Learning with Driverless AI Use Driverless AI to build, tune, and interpret machine learning models in a streamlined workflow.
Model Deployment for Business Impact
Deploy AI models into production environments to drive actionable outcomes.
Generative AI Applications
Leverage tools like h2oGPT and Enterprise GPTe for text generation, summarization, and language translation tasks.
Course Playlist on YouTube
Explore H2O.ai’s Managed Cloud—your secure, enterprise-grade environment for building, deploying, and scaling AI and machine learning solutions. In this quick walkthrough, discover how to:
✅ Access enterprise tools for managing models and workflows
✅ Use the App Store to launch apps like Enterprise H2O GPTe and Driverless AI
✅ Organize projects using personal and team workspaces
✅ Manage compute resources, secrets, and operations with ease
✅ Get instant support with built-in ticketing and documentation tools
Whether you’re working with predictive or generative AI, H2O.ai’s Managed Cloud empowers your team with everything you need in one flexible platform.
👉 Learn more and get started today at https://www.h2o.ai
#H2Oai #ManagedCloud #EnterpriseAI #MachineLearning #AIInfrastructure #LLM #AutoML #GenAI
Want to learn how H2O.ai's platform simplifies data science workflows with seamless integration across features, notebooks, and AI engines like Driverless AI?
This is the right place for you!
In this course, you will be guided through project planning with feature sets, interacting with features via UI and notebooks, and visualizing data pipelines.
You will also see how the feature store allows organizing projects, controlling access, versioning datasets, and deriving new features.
Explore the notebook lab with sample notebooks, GitHub integration, and easy authorization.
Enjoy!
Discover how H2O's Driverless AI empowers data scientists with automated machine learning, data visualization, prep wizards, and live coding capabilities.
Here's how to access H2O's Driverless AI for training purposes:
1. Visit our Aquarium platform at https://aquarium.h2o.ai/.
2. Watch the following video to learn how to create an account on Aquarium: https://youtu.be/2V9XCT7dDqk?si=7KAvIUw9Fcc-fcZ2 .
3. After you've gained access to Aquarium, navigate to the Driverless AI Training (1.10.5 LTS).
4. Start an instance to access the user interface through the Driverless AI URL link provided at the bottom of the page. The instance will be available for your to use for 120 minutes, at the end of which all its data will be erased. Enjoy your training session with Driverless AI!
Learn how to effortlessly upload datasets and leverage existing ones from the feature store for analysis. Follow along as we explore the intuitive interface's ability to extract column names, generate data summaries, and execute Python functions seamlessly.
Experience the latest innovation from H2O, H2O Functions, a chat-based interface for data science tasks. Learn how to leverage this powerful tool to perform various functions directly from a chat-based interface, enhancing collaboration and accessibility for users of all skill levels.
Witness how Driverless AI automates code generation and visualization using libraries like seaborn and matplotlib, offering valuable insights into data distributions.
Discover additional functionalities, such as model building and interpretation explanations, empowering users of all levels to interact with automated machine learning tools.
Lastly, dive into the generated code available in notebooks for further customization by Python enthusiasts and data scientists.
Learn how to leverage H2O, an open-source library, to effortlessly create multi-page applications and chatbots using only Python. Explore the process of deploying these apps to the iCloud for seamless accessibility across your organization.
In this demo, we delve into the Rupogen Gen AI App Store in GitHub, featuring over 15 example applications in the Gen AI space, perfect for building chatbots or applications utilizing LLMs in the background. In addition, experience the capabilites of Wave, as we demonstrate how to run applications locally with simple commands, bringing your ideas to life effortlessly.
Follow along as we dive into the Python code behind these applications, showcasing how to create dynamic interfaces without the need for complex JavaScript or CSS. Discover the ease of adapting your applications for mobile devices, ensuring a seamless user experience across all platforms.
Explore the process of training and deploying a standalone Large Language Model (LLM) with guardrails in this engaging demo.
Witness the stark difference between an unguarded LLM generating whimsical, off-brand responses and one with carefully implemented guardrails, maintaining professionalism and coherence across various prompts.
Explore real-world examples, such as crafting LinkedIn posts, where the guardrailed LLM effortlessly captures the appropriate voice and context, while the unguarded model deviates, potentially compromising brand integrity.
Ready to dive in? Gain access to LLM DataStudio and H2O LLM Studio for your training endeavors:
1. Visit our Aquarium platform at https://aquarium.h2o.ai/.
2. Follow the steps in the video tutorial to create an account on Aquarium: https://youtu.be/2V9XCT7dDqk?si=7KAvIUw9Fcc-fcZ2.
3. Once you're in Aquarium, navigate to the LLM Data Studio Lab or H2O LLM Data Studio Lab, depending on your requirements.
4. Launch an instance to access the user interface via the provided URL link at the bottom of the page. The instance will remain available for 120 minutes, after which all data will be erased. Enjoy your training session!
In this demo, we navigate the H2O AI Cloud, where Enterprise GPTe, H2O GPT, and Eval Studio await exploration. Witness the creation of collections, the import of documents, and the utilization of generative AI to extract insights from complex data sets.
Follow along as we converse with documents, using large language models to provide feedback via a RAG system. Gain insights into the process of parsing, chunking, and embedding data for meaningful interactions.
Explore the customizable settings of Enterprise GPTe, from system prompts to advanced RAG configurations, and discover how to optimize AI performance while managing costs effectively.
Delve into the API capabilities, from connecting to loading data to creating chat sessions, and learn how to harness the power of generative AI for your specific use cases.
Witness the evaluation of AI models and RAG systems in Eval Studio, where you can create custom leaderboards, define evaluation metrics, and analyze performance across various models and scenarios.
Ready to unlock the potential of generative AI?
Get Started Now using H2O Enterprise GPTe: https://h2o.ai/#gpt
Explore H2O.ai: https://h2o.ai/
💡 Want to build AI models that maximize business value? This video explores how the H2O platform helps optimize models for real-world impact.
🚀 Learn how to:
✅ Reduce customer churn by 20% using AI
✅ Use the Business Value Calculator to compare model profits
✅ Adjust accuracy, interpretability, and latency for different use cases
✅ Make data-driven decisions to optimize AI in production
🔗 Try it now with H2O.ai and take your AI projects to the next level!
#AI #MachineLearning #CustomerChurn #BusinessIntelligence #DataScience
💡 Discover how to use h2oGPTe for collaborative, research-based hypothesis testing! In this video, we explore how AI can help predict and optimize customer churn by analyzing the impact of pricing changes.
🚀 Learn how to:
✅ Use AI to test business hypotheses in real-time
✅ Analyze customer churn based on pricing strategies
✅ Collaborate with teams for data-driven decision-making
✅ Optimize pricing to balance revenue and retention
Watch as we experiment with a 10% price reduction on day minutes and evaluate its impact on revenue and customer retention. Can AI help find the best price point to minimize churn? Let’s find out!
🔗 Try h2oGPTe today and start making smarter business decisions with AI!
#AI #MachineLearning #HypothesisTesting #CustomerChurn #DataScience
Learn how to efficiently manage projects and feature sets using Feature Store in H2O. This video explores how organizations can improve collaboration, access control, and versioning to optimize AI workflows.
Key takeaways:
✅ Discover and collaborate on public projects in Feature Store
✅ Manage access to private and locked projects securely
✅ Assign roles and distribute tasks efficiently within your organization
✅ Track feature sets, data versions, and historical predictions
Feature Store enables better AI modeling by ensuring seamless data access and version control. Learn how to derive features, schedule tasks, and retrieve the latest data for your models.
#AI #FeatureStore #MachineLearning #DataScience #H2O
Learn how data lineage in the H2O platform ensures transparency, traceability, and efficiency in AI model development. Feature Store and Driverless AI provide seamless tracking of data from feature creation to model deployment.
Key insights:
✅ Collaborate on feature sets with version control
✅ Track changes and dependencies in derived feature sets
✅ Automatically document model data for full transparency
✅ Trace training data back to experiments and model versions
By maintaining a clear data lineage, organizations can optimize their AI workflows, ensure reproducibility, and build more reliable models.
#AI #DataLineage #MachineLearning #FeatureStore #H2O
Explore how data profiling and augmentation enhance AI model performance in AutoML. From data quality checks to feature engineering, learn how to optimize datasets for better predictions.
Key insights:
✅ Use AutoViz to visualize key dataset patterns
✅ Detect and resolve missing data and leakage issues automatically
✅ Apply smart feature engineering to improve model accuracy
✅ Utilize h2oGPTe agents for automatic data cleaning and optimization
✅ Generate new datasets with Enterprise LM Studio for fine-tuning
By leveraging automated data insights, you can ensure your models are built on high-quality, optimized data for better performance.
#AI #MachineLearning #AutoML #DataAugmentation #H2O
Learn how H2O AutoInsights automatically extracts valuable insights from your data using statistical and machine learning analysis. Gain a deeper understanding of your datasets with interactive visuals and AI-powered narrative summaries.
Key insights:
✅ Generate frequency, correlation, and cluster analysis automatically
✅ Detect and analyze anomalies in time series data
✅ Use Enterprise H2O GPTe to enhance AI-driven insights
✅ Integrate with Driverless AI for model creation and performance metrics
✅ Identify key predictors and business recommendations for decision-making
By leveraging H2O AutoInsights, you can automate data exploration, improve predictions, and make smarter business decisions with AI-powered insights.
#AI #DataAnalysis #MachineLearning #H2O #DataInsights
Discover how H2O supports Causal AI with uplift modeling in Driverless AI and H2O3. Learn how to evaluate the impact of treatments versus control groups to optimize marketing campaigns, customer engagement, and decision-making.
Key insights:
✅ Use uplift modeling to measure the impact of interventions
✅ Apply LightGBM, XGBoost, GLM, and Uplift Random Forest for causal AI
✅ Perform stratification checks to ensure fair treatment vs. control groups
✅ Leverage Driverless AI custom recipes for advanced modeling
✅ Identify key variables influencing customer responses
With H2O’s Causal AI capabilities, you can make data-driven decisions that maximize impact and efficiency.
#AI #CausalAI #MachineLearning #UpliftModeling #H2O
Learn how Disparate Impact Analysis helps assess fairness in Driverless AI models and detect potential bias in decision-making. This method ensures AI models provide equitable outcomes across different demographic groups.
Key insights:
✅ Evaluate model fairness by analyzing disparate impact variables
✅ Compare treatment of different demographic groups (e.g., gender, race)
✅ Measure fairness using metrics like F1 score and cut-off probability
✅ Visualize classification outcomes and adverse impact ratios
✅ Utilize custom fairness recipes available on the H2O GitHub repository
With AI fairness tools, organizations can build more ethical models and reduce bias in automated decisions.
#AI #Fairness #BiasDetection #MachineLearning #H2O
Discover how h2oGPTe integrates predictive and generative AI to automate model training, deployment, and application building. See how AI agents streamline workflows and generate Python code, visualizations, and model insights automatically.
Key insights:
✅ Train AI models with automated function-calling agents
✅ Use generative AI to write and execute Python code for model development
✅ Deploy models and perform drift detection with H2O Driverless AI
✅ Auto-generate synthetic data and scoring scripts for AI models
✅ Build AI-powered applications using Streamlit and h2oGPTe
With h2oGPTe, you can leverage AI agents to accelerate model training, automate deployments, and optimize predictive analytics.
#AI #MachineLearning #AutoML #h2oGPTe #GenerativeAI
Explore how predictive and generative AI enhance model validation, evaluation, and compliance within the H2O platform. Learn how to fine-tune AI performance while ensuring fairness, security, and efficiency.
Key insights:
✅ Customize Driverless AI experiments with expert settings for regulatory compliance
✅ Generate automatic model documentation for risk management
✅ Implement guardrails and PII redaction in generative AI models
✅ Evaluate model performance, fairness, and bias using inline evaluations
✅ Use retrieval-augmented generation (RAG) for advanced model assessment
With H2O’s AI tools, organizations can build trustworthy models, ensure compliance, and optimize AI-driven decision-making.
#AI #MachineLearning #ModelValidation #GenerativeAI #H2O
feature metadata, permissions, and access control to improve collaboration and model development.
Key insights:
✅ Store, update, and reuse feature sets for ML models
✅ Leverage automatic feature engineering from Driverless AI
✅ Access both online and offline feature stores for scalable data retrieval
✅ Set permissions and access controls for secure data management
✅ Explore public projects and collaborate on ML feature sets
With H2O Feature Store, teams can improve model efficiency, enable secure collaboration, and accelerate AI-driven insights.
#AI #MachineLearning #FeatureStore #DataManagement #H2O
Discover how Driverless AI streamlines model experiment tracking and resource optimization by running multiple AI models in parallel. Learn how automatic queuing ensures efficient CPU & GPU utilization while minimizing idle time.
Key insights:
✅ Automatically queue and execute multiple model experiments
✅ Optimize resource usage with dynamic CPU and GPU allocation
✅ Use the Compare Experiments tool to analyze model setups and results
✅ Evaluate variable importance and prediction accuracy across experiments
✅ Reproduce results using Driverless AI’s reproducibility settings
With Driverless AI, organizations can accelerate model development, improve efficiency, and gain deeper insights into AI experiments.
#AI #MachineLearning #ModelExperiments #DriverlessAI #H2O
Learn how to store, share, and manage AI model experiments in Driverless AI for seamless collaboration and deployment. See how MLOps integration enables efficient model tracking, versioning, and deployment.
Key insights:
✅ Add completed experiments to centralized projects for easy access
✅ Share projects with MLOps engineers and team members
✅ View and analyze validation scores, metadata, and model parameters
✅ Register models and manage versioning for future deployments
✅ Use H2MLOps to track experiments and streamline AI workflows
With Driverless AI and H2MLOps, organizations can enhance AI collaboration, track model performance, and optimize deployment strategies.
#AI #MachineLearning #DriverlessAI #MLOps #ModelDeployment
Learn best practices for interpreting AI models in Driverless AI, ensuring transparency, fairness, and clear communication of limitations. Explore tools like sensitivity analysis and disparate impact analysis to assess model fairness and performance.
Key insights:
✅ Use sensitivity analysis to test model responses under different conditions
✅ Perform disparate impact analysis to detect potential bias
✅ Document model limitations for DevOps and end-users
✅ Add tags and comments in H2MLOps to track model usage guidelines
✅ Improve AI transparency and accountability in deployment
By integrating interpretability tools, organizations can ensure responsible AI usage and make informed deployment decisions.
#AI #MachineLearning #FairnessInAI #ModelInterpretation #DriverlessAI
Learn how to deploy AI models efficiently using H2O MLOps, with support for A/B testing, Champion-Challenger setups, and scalable environments. Explore different deployment templates and scoring pipelines for maximum flexibility.
Key insights:
✅ Deploy models in development or production environments
✅ Choose between single-model or multi-model deployments
✅ Use prediction-only or prediction + reason codes for explainability
✅ Download and use Python scoring pipelines or Mojo models
✅ Deploy Mojo models in databases like Snowflake, Teradata, Hive, or cloud environments
With H2O MLOps, organizations can streamline AI deployment, enhance model performance, and integrate predictions seamlessly into business applications.
#AI #MachineLearning #ModelDeployment #MLOps #DriverlessAI
Explore how H2O’s AI platform supports the full model lifecycle, from registration and deployment to automated retraining and deactivation. Learn how to manage models efficiently using H2O MLOps and Python APIs.
Key insights:
✅ Register and manage new or versioned models in MLOps
✅ Use Champion-Challenger and A/B testing for gradual model deployment
✅ Deactivate underperforming models with a single click
✅ Automate retraining and deployment workflows with Python APIs
✅ Monitor model drift and trigger automatic model updates
With H2O’s AI automation, teams can streamline model management, improve performance, and ensure models stay up-to-date with real-world data.
#AI #MachineLearning #MLOps #ModelLifecycle #DriverlessAI
Learn how Driverless AI enables real-time model monitoring, drift detection, and performance tracking for AI models in production. See how to analyze predictions, detect changes, and automate alerts for model performance issues.
Key insights:
✅ Track real-time predictions and scoring latency
✅ Detect feature drift with threshold-based alerts
✅ Visualize distributional changes in key features
✅ Use APIs and agentic AI solutions for advanced drift analysis
✅ Automate prediction requests and statistical comparisons
With Driverless AI’s monitoring tools, organizations can proactively manage AI models, reduce drift impact, and maintain high prediction accuracy.
#AI #MachineLearning #ModelMonitoring #DriftDetection #DriverlessAI
Discover how Driverless AI enables AI models to self-identify and handle issues in real-time. Learn how monitoring, drift detection, and error handling ensure robust and reliable AI deployments.
Key insights:
✅ Monitor prediction volume and latency in real-time
✅ Detect and analyze model drift for proactive updates
✅ Validate input data types to prevent incorrect predictions
✅ Automate error handling and response codes for better stability
✅ Ensure seamless AI model performance with built-in safeguards
With Driverless AI’s intelligent monitoring and validation tools, organizations can enhance AI reliability, reduce errors, and maintain high-quality model performance.
#AI #MachineLearning #ModelMonitoring #ErrorHandling #DriverlessAI
1
4:17
H2O.ai Managed Cloud Overview | Build & Scale AI Across Your Enterprise
2
0:25
Introduction to H2O.ai's Data Science and Machine Learning Platform
3
5:19
Plan Projects, Explore , Visualize, Data Preparation
4
8:17
Data Science and Machine Learning Techniques
5
4:12
Model Consumption with H2O.ai Tools
6
22:10
Training and Deploying Standalone LLM + Guardrails
7
16:56
Generative AI for Advanced RAG systems & AI Governance
8
2:30
How to Choose the Best AI Model for Business Success | Reduce Customer Churn by 20%
9
2:01
Using AI for Hypothesis Testing | Optimize Customer Churn with h2oGPTe
10
1:49
Managing Projects and Feature Sets in Feature Store | Optimizing Data Access for AI
11
1:31
Understanding Data Lineage in H2O | Tracking Data for AI Models
12
1:45
Data Profiling and Augmentation for AutoML | Improving AI Model Accuracy
13
2:00
Uncovering Data Insights with H2O AutoInsights | AI-Powered Data Analysis
14
3:17
Causal AI and Uplift Modeling with H2O | Analyzing Treatment vs. Control Groups
15
1:58
Ensuring Fairness in AI with Disparate Impact Analysis | Bias Detection in Machine Learning
16
3:07
Harnessing Predictive & Generative AI with h2oGPTe | Automating Model Training & Deployment
17
5:11
Optimizing AI Models with Predictive & Generative AI | Model Validation & Evaluation
18
1:10
Enhancing Machine Learning with H2O Feature Store | Efficient Feature Management
19
2:00
Optimizing AI Model Experiments with Driverless AI | Parallel Experiment Tracking
20
1:40
Managing AI Model Experiments in Driverless AI | Collaboration & MLOps Integration
21
1:48
Interpreting AI Models in Driverless AI | Fairness, Sensitivity & Model Transparency
22
1:45
Deploying AI Models with H2O MLOps | Scalable & Flexible Deployment Strategies
23
2:01
Managing the Full AI Model Lifecycle with H2O | Automation, Retraining & Deployment
24
1:59
Monitoring AI Model Performance & Drift in Driverless AI | Real-Time Insights & Automation
25
1:14
Self-Identifying & Fixing AI Model Issues | Automated Error Handling in Driverless AI
As the Head of Product at H2O.ai, Michelle Tanco’s primary focus lies in delivering a seamless user experience across machine learning applications. With a strong dedication to math and computer science, she is enthusiastic about leveraging these disciplines to address real-world challenges. Before joining H2O, she served as a Senior Data Science Consultant at Teradata, working on high-impact analytics projects to tackle business issues across various industries. Michelle holds a B.A. in Mathematics and Computer Science from Ursinus College. In her downtime, she enjoys spending quality time with her family and expressing her creativity by playing the bass and ukulele.
Jon Farland, Director of Solutions Eng.
Jon Farland is the Director of the H2O.ai Solutions Engineering team. He has spent the better part of the last decade building analytical solutions at the intersection of technology, finance and energy. He has used H2O extensively to develop high performing models, communicate findings across stakeholders and to lead ROI growth from data science initiatives.
Audrey Létévé, Principal Customer Data Scientist
Principal Data Scientist at H2O.ai, specializing in leading complex Machine Learning projects from ideation to production, with a keen interest in Model Ops and a strong background in statistics.
Her expertise covers a broad range of industries such as insurance, energy, and services, enabling her to communicate effectively with both technical and non-technical stakeholders.
Holding a Master of Science in Mathematics and Statistics from Université Aix-Marseille II, Audrey has a proven track record of enhancing business strategies and objectives through data analysis and model development across various data science roles.