Getting started with IBM watsonx.ai

Use IBM watsonx.ai to train, validate, tune, and deploy generative AI solutions with foundation models.

The collection of foundation models in watsonx.ai™ support a range of use cases for both natural languages and programming languages. You can choose between large language models from IBM and other providers or deploy your own custom foundation models that best suit your solution.

You can create effective prompts in the Prompt Lab, a tool designed to help you prompt foundation models. You can store prompts as prompt template assets that you can reuse and share with others. You can also store the prompt as a notebook asset. The prompt text, model reference, and prompt engineering parameters are formatted as Python code in a notebook that you can interact with programmatically.

You can guide a foundation model to return customized output that better meets your needs by using the Tuning Studio, a tool that lets you modify a foundation model's responses or behavior by tuning the model with specialized data.