Skip to main content
This reference documents the UI elements, configuration options, and actions available in the Prompt Studio interface.

​
Overview

Prompt Studio transforms datasets into structured, fine-tuning-ready examples for AI models. Each row in the output dataset represents a valid training example formatted as a conversation with system, user, and assistant messages. Path: My Models → Prompt Studio

​
Prompt Builder module

The Prompt Builder is the main workspace for configuring how dataset rows transform into conversation-formatted training examples.

​
Dataset selector

ElementDescription
Dataset dropdownSelect the source dataset to transform
Row countDisplays total rows available for transformation
The selected dataset provides the fields available for macro substitution in prompts.

​
Role configuration panels

Three panels allow you to configure prompts for each conversation role:
RolePurposeTypical content
SystemSets the AI’s behavior and contextInstructions, persona definition, constraints
UserRepresents the human inputQuestions, requests, data to analyze
AssistantRepresents the AI responseExpected output format, example responses
Each panel contains:
ElementDescription
Select buttonOpens the prompt editor for that role
Prompt text areaDisplays the configured prompt with macro placeholders
Macro indicatorsVisual badges showing embedded macros

​
Prompt editor

The prompt editor opens when you click Select on any role panel.

​
Text input area

ElementDescription
Prompt text fieldMulti-line text area for writing the prompt
Macro placeholder syntaxUse {{macro_name}} to insert dynamic values
Character countDisplays current prompt length

​
Macro configuration

After adding macro placeholders to your prompt text, configure each macro’s data source:
Macro typeDescriptionUse case
FieldMaps to a column in the source datasetPull values directly from dataset columns
NQLUses a Narrative Query Language expressionCompute derived values, transform data, combine fields
LiteralFixed text valueStatic content that doesn’t change per row

​
Macro configuration panel

ElementDescription
Macro nameThe identifier used in {{macro_name}} syntax
Type selectorChoose between Field, NQL, or Literal
Value configurationField picker, NQL editor, or text input based on type
Preview valueSample resolved value from the first dataset row

​
Editor actions

ActionDescription
SaveSaves the prompt configuration and returns to Prompt Builder
CancelDiscards changes and returns to Prompt Builder

​
Preview screen

The Preview screen validates your prompt configuration by showing resolved output for each dataset row. Path: Click Preview in the Prompt Builder

​
Conversation display

ElementDescription
System messageResolved system prompt with all macros substituted
User messageResolved user prompt with all macros substituted
Assistant messageResolved assistant prompt with all macros substituted
Messages display in a conversational format, visually distinguishing each role.
ControlDescription
PrevNavigate to the previous dataset row
NextNavigate to the next dataset row
Row indicatorShows current row number and total (e.g., “Row 5 of 1,234”)

​
Validation indicators

IndicatorMeaning
Green checkmarkAll macros resolved successfully
Yellow warningSome macros returned empty or null values
Red errorMacro resolution failed (e.g., invalid NQL expression)

​
Output format

The transformed dataset contains rows formatted as structured conversations: 
{
  "messages": [
    { "role": "system", "content": "You are a helpful assistant..." },
    { "role": "user", "content": "Analyze this customer data..." },
    { "role": "assistant", "content": "Based on the data provided..." }
  ]
}
This format is compatible with fine-tuning APIs from major AI model providers.

​
Actions reference

​
Builder actions

ActionLocationDescriptionResult
Select datasetDataset moduleChoose source datasetDataset fields become available for macros
Configure roleRole panelOpen prompt editor for a rolePrompt editor opens
PreviewPrompt Builder toolbarValidate prompt resolutionPreview screen opens

​
Editor actions

ActionLocationDescriptionResult
Add macroPrompt textType {{name}} syntaxMacro placeholder created
Configure macroMacro panelSet type and valueMacro resolution configured
SaveEditor toolbarSave prompt configurationReturns to Prompt Builder

​
Preview actions

ActionLocationDescriptionResult
Navigate rowsNavigation controlsView different dataset rowsConversation updates with new row data
Return to builderPreview toolbarExit preview modeReturns to Prompt Builder

​
Output actions

ActionLocationDescriptionResult
Generate datasetPrompt Builder toolbarCreate materialized datasetOpens Data Studio with prompt configuration

​
Workflow summary

  1. Select dataset → Choose source data in the Dataset module
  2. Configure prompts → Define system, user, and assistant prompts with macros
  3. Configure macros → Map each macro to a field, NQL expression, or literal value
  4. Preview output → Validate resolved prompts row by row
  5. Generate dataset → Use Data Studio to materialize the transformed dataset

​
Related content

LLM Studio

Train and fine-tune models using prepared datasets

NQL Syntax

Reference for NQL expressions used in macros

Model Inference

Using AI models within your data plane

Creating Materialized Views

Generate datasets from your prompt configurations