Take quick start tutorials to learn how to perform specific tasks, such as refine data or build a model. These tutorials help you quickly learn how to do a specific task or set of related tasks.
The quick start tutorials are categorized by task:
- Preparing data
- Analyzing and visualizing data
- Building, deploying, and trusting models
- Working with generative AI
- Governing AI
Each tutorial requires one or more service instances. Some services are included in multiple tutorials. The tutorials are grouped by task. You can start with any task. Each of these tutorials provides a description of the tool, a video, the instructions, and additional learning resources.
The tags for each tutorial describe the level of expertise (, , or ), and the amount of coding required (, , or ).
After completing these tutorials, see the Other learning resources section to continue your learning.
Preparing data
To get started with preparing, transforming, and integrating data, understand the overall workflow, choose a tutorial, and check out other learning resources for working on the platform.
Your data preparation workflow has these basic steps:
-
Create a project.
-
If necessary, create the service instance that provides the tool you want to use and associate it with the project.
-
Add data to your project. You can add data files from your local system, data from a remote data source that you connect to, or sample data from the Resource hub.
-
Choose a tool to analyze your data. Each of the tutorials describes a tool.
-
Run or schedule a job to prepare your data.
Tutorials for preparing data
Each of these tutorials provides a description of the tool, a video, the instructions, and additional learning resources:
| Tutorial | Description | Expertise for tutorial |
|---|---|---|
| Refine and visualize data with Data Refinery | Prepare and visualize tabular data with a graphical flow editor. | Select operations to manipulate data. |
| Generate synthetic tabular data | Generate synthetic tabular data using a graphical flow editor. | Select operations to generate data. |
Analyzing and visualizing data
To get started with analyzing and visualizing data, understand the overall workflow, choose a tutorial, and check out other learning resources for working with other tools.
Your analyzing and visualizing data workflow has these basic steps:
-
Create a project.
-
If necessary, create the service instance that provides the tool you want to use and associate it with the project.
-
Add data to your project. You can add data files from your local system, data from a remote data source that you connect to, or sample data from the Resource hub.
-
Choose a tool to analyze your data. Each of the tutorials describes a tool.
Tutorials for analyzing and visualizing data
Each of these tutorials provides a description of the tool, a video, the instructions, and additional learning resources:
| Tutorial | Description | Expertise for tutorial |
|---|---|---|
| Analyze data in a Jupyter notebook | Load data, run, and share a notebook. | Understand generated Python code. |
| Refine and visualize data with Data Refinery | Prepare and visualize tabular data with a graphical flow editor. | Select operations to manipulate data. |
Building, deploying, and trusting models
To get started with building, deploying, and trusting models, understand the overall workflow, choose a tutorial, and check out other learning resources for working on the platform.
The different stages involved in the AI lifecycle are as follows:
- Define scope: Start by defining the scope of your project by identifying the key objectives and requirements.
- Prepare data: Collect and prepare data for use with machine learning algorithms.
- Build model: Develop and refine the AI model to solve the defined problem by training the model with prepared data.
- Deploy model: Deploy the model to production after the building process is complete.
- Automate pipeline: Automate the path to production by automating parts of the AI lifecycle.
- Monitor performance: Evaluate your model's performance for fairness, quality, drift and explainability.
The following diagram shows the stages of the AI lifecycle:
Your workflow to build, deploy, and trust models has these basic steps:
-
Create a project.
-
If necessary, create the service instance that provides the tool you want to use and associate it with the project.
-
Choose a tool to build, deploy, and trust models. Each of the tutorials describes a tool.
Tutorials for building, deploying, and trusting models
Each tutorial provides a description of the tool, a video, the instructions, and additional learning resources:
| Tutorial | Description | Expertise for tutorial |
|---|---|---|
| Build and deploy a machine learning model with AutoAI | Automatically build model candidates with the AutoAI tool. | Build, deploy, and test a model without coding. |
| Build and deploy a machine learning model in a notebook | Build a model by updating and running a notebook that uses Python code and the watsonx.ai Runtime APIs. | Build, deploy, and test a scikit-learn model that uses Python code. |
| Build and deploy a machine learning model with SPSS Modeler | Build a C5.0 model that uses the SPSS Modeler tool. | Drop data and operation nodes on a canvas and select properties. |
| Build and deploy a Decision Optimization model | Automatically build scenarios with the Modeling Assistant. | Solve and explore scenarios, then deploy and test a model without coding. |
| Automate the lifecycle for a model with pipelines | Create and run a pipeline to automate building and deploying a machine learning model. | Drop operation nodes on a canvas and select properties. |
| Evaluate a machine learning model | Deploy a model, configure monitors for the deployed model, and evaluate the model. | Run a notebook to configure the models and use Watson OpenScale to evaluate. |
Working with generative AI
To get started with working with generative AI, understand the overall workflow, choose a tutorial, and check out other learning resources for working on the platform.
Your prompt engineering workflow has these basic steps:
-
Create a project.
-
If necessary, create the service instance that provides the tool you want to use and associate it with the project.
-
Choose a tool to prompt foundation models. Each of the tutorials describes a tool.
-
Save and share your best prompts.
Tutorials for working with generative AI
Each tutorial provides a description of the tool, a video, the instructions, and additional learning resources:
| Tutorial | Description | Expertise for tutorial |
|---|---|---|
| Prompt a foundation model using Prompt Lab | Experiment with prompting different foundation models, explore sample prompts, and save and share your best prompts. | Prompt a model using Prompt Lab without coding. |
| Prompt a foundation model with the retrieval-augmented generation pattern | Prompt a foundation model by leveraging information in a knowledge base. | Use the retrieval-augmented generation pattern in a Jupyter notebook that uses Python code. |
| Tune a foundation model | Tune a foundation model to enhance model performance. | Use the Tuning Studio to tune a model without coding. |
| End-to-end watsonx.ai tutorial | Build your model using any of the tools, such as AutoAI, SPSS Modeler, or Jupyter notebooks, followed by deploying and testing your model. Further, transform your data and tune your foundation model by using watsonx.ai. |
Governing AI
To get started with governing AI, understand the overall workflow, choose a tutorial, and check out other learning resources for working on the platform.
Your AI governance workflow has these basic steps:
-
Create a project.
-
If necessary, create the service instance that provides the tool you want to use and associate it with the project.
-
Choose a tool to govern AI. Each of the tutorials describes a tool.
Tutorials for governing AI
Each tutorial provides a description of the tool, a video, the instructions, and additional learning resources:
| Tutorial | Description | Expertise for tutorial |
|---|---|---|
| Evaluate and track a prompt template | Evaluate a prompt template to measure the performance of foundation model and track the prompt template through its lifecycle. | Use the evaluation tool and an AI use case to track the prompt template. |
| Compare prompt performance | Evaluate and compare your generative AI assets with quantitative metrics and customizable criteria that fit your use cases. | Use the Evaluation Studio to evaluate the performance of multiple assets simultaneously. |
| Evaluate a machine learning model | Deploy a model, configure monitors for the deployed model, and evaluate the model Watson OpenScale. | Run a notebook to configure the monitors and use Watson OpenScale to evaluate. |
| Evaluate a deployment in spaces | Deploy a model, configure monitors for the deployed model, and evaluate the model in a deployment space. | Configure the monitors and evaluate a model in a deployment space. |
Other learning resources
Guided tutorials
Access the Build an AI model sample project to follow a guided tutorial in the Resource hub. After you create the sample project, the readme provides instructions:
- Choose Explore and prepare data to remove anomalies in the data with Data Refinery.
- Choose Build a model in a notebook to build a model with Python code.
- Choose Build and deploy a model to automate building a model with the AutoAI tool.
Watch this video series to see how to work with the assets in the sample project.
General
Preparing data
Analyzing and visualizing data
Building, deploying, and trusting models
Working with generative AI
Governing AI
Videos
- A comprehensive set of videos that show many common tasks in watsonx.
Samples
Find sample data sets, projects, models, prompts, and notebooks in the Resource hub area to gain hands-on experience:
Notebooks that you can add to your project to get started analyzing data and building models.
Projects that you can import containing notebooks, data sets, prompts, and other assets.
Data sets that you can add to your project to refine, analyze, and build models.
Prompts that you can use in the Prompt
Lab to prompt a foundation model.
Foundation models that you can use in the Prompt Lab.
Use case samples
Try out different use cases on a self-service site. Select a use case to experience a live application built with watsonx. Developers, access prompt selection and construction guidance, along with sample application code, to accelerate your project.
Parent topic: Getting started