Skip to main content
Use AI Prompt when you want a workflow step to send a prompt to an LLM and store the assistant response for later steps.

​
Configuration

In Parameters, the exact controls change with the selected model:
  • Temperature is shown for standard models.
  • Max Thinking Tokens is shown for manual-budget Anthropic Claude and Google Gemini thinking models.
  • Reasoning Effort is shown for adaptive Claude models such as Claude Sonnet 4.6+, Claude Opus 4.6+, Claude Opus 5, and Claude Fable 5.
  • Reasoning Effort is shown for OpenAI and xAI reasoning models (low / medium / high).
  • Reasoning (enabled/disabled) is shown for supported third-party reasoning models such as Cohere.
In Prompt, click Add Message to build the message list. The first new message is a system message. After that, new messages default to user. Each message supports variable insertion from the workflow with the Insert Variable button. For vision-capable models, user messages can also include an image URL. If your selected provider supports structured output, you can enable JSON Schema in Response Format. This opens a schema editor where you can set a schema name, load an example, and save the JSON schema the model must follow. assistant is available as a message role in the editor, but this step still runs as a single prompt execution and stores the final assistant response as the step output.

​
Output

This step stores the final assistant response as the step output. Use the variable picker to insert the exact reference path for a previous prompt step. In templates and later steps, the base reference is:
If the response is plain text, reference the full value directly:
If JSON Schema is enabled and the model returns a structured object, you can reference nested fields:
The exact available keys depend on the schema and model response shown in the variable picker.

​
Example

Add AI Prompt from the workflow step picker. Set Name to something like Summarize article. In Parameters, choose your Charge Type and LLM Model. Adjust Temperature, Reasoning Effort, Max Thinking Tokens, or the Reasoning toggle if those controls are shown for your model. In Prompt, add a system message that explains the task and a user message that inserts earlier workflow data such as {{step_1.output}}. If you need structured output, enable JSON Schema and define fields such as title and summary. Click Run in the step header to test the step. The response appears in the right-hand panel, and later steps can reference that output with the variable picker.

​
Notes

  • Use the step identifier shown in the variable picker when you reference this step in later fields.
  • The Clear action removes previous model responses from the test panel. It does not remove your prompt messages.
  • The step output is the final assistant response, not the full request metadata.
  • When JSON Schema is enabled, later steps can reference the returned object by field instead of parsing raw text.
  • When the workflow copilot adds or edits an AI Prompt step for you, it writes three messages: a system message (objective, edge cases, staying on task), a user message with Instructions/Steps/Output Format/Examples/Notes sections, and — only when the step takes input from an earlier step or a workflow variable — a final user message holding just the variable placeholders (like {{step_1.output}}). Keeping placeholders in that last message keeps the rest of the prompt unchanged between runs, which helps Fetch Hive reuse the unchanged part of the prompt for models that support prompt caching.
See also: Creating and Editing, Testing and Iteration, and Use your own API Key