Glossary

Foundation models are large, pretrained AI models that can be adapted to many tasks—like writing, coding, or image analysis—making them a powerful starting point for building AI applications.

Latency is the delay between input and response—lower latency means faster results.

Model serving is the process of making a trained AI model available for use in real time or batch mode, so it can receive input and return predictions through an API or service.

Benchmarking is the process of comparing your performance, products, or processes to the best in the industry to identify ways to improve.