Overview

Create standalone prompts, test them in the editor, version changes, and run them through prompt deployments

Use prompts when you want to write and test a single LLM interaction without building a full workflow. In this section, you'll create prompts, work with inputs, save versions, create prompt deployments, and review prompt activity.

Standalone prompts are different from prompt steps inside workflows. These pages cover the prompt editor under Prompts, not the workflow builder under Workflows.

What you'll find here

• Creating and Editing - Create a prompt, add messages, work with inputs, and test it in the editor

• Publishing and Versioning - Save versions, review version history, roll back changes, and create prompt deployments

• Run with API - Invoke a prompt deployment with cURL using the public API

• Logs - Review prompt runs, request details, inputs, and related activity

• Run with Python SDK - Python SDK docs are not available yet

• Run with Node.js SDK - Node.js SDK docs are not available yet