Langsmith
LangSmith is a unified observability and evaluations platform where teams can debug, test, and monitor the performance of AI applications.
Introduction
LangSmith supports you at every step of your development journey with tools for observability, evaluation, and prompt engineering.
Getting LLMs to respond appropriately can sometimes feel more like an art than a science.
Playground
Prompt engineering is key to LLM application development because the quality of a prompt directly affects the LLM’s output.
With the right prompts, you can ensure that your application delivers accurate, relevant, and reliable responses.
The LangSmith Playground is a space to experiment with different prompts and models across various inputs, which lets you quickly see how changes affect the response.
Check out the Playground documentation to get started!
Next, we’ll talk about how to manage your prompts.
Prompts
Estás leyendo una vista previa.
Inicia sesión con Google para leer la página completa. Sigue el itinerario de aprendizaje — cada página se desbloquea cuando has leído las que la preceden. El alumnado y el profesorado leen las páginas de su curso sin límite.
Iniciar sesión