Prompts

Prompts store all configuration for interacting with a model: system instructions, messages, model selection, and parameters. A Prompt can be reused across Playgrounds, Experiments, Deployments, and Agents.

Use Cases

Standardize AI Behavior Across Teams

Use prompts as shared instructions so every team and application produces consistent, aligned outputs.

Turn AI Use Cases into Reusable Assets

Package prompts as configurable building blocks that can be reused across products, workflows, and experiments.

Control Model Output Without Code Changes

Adjust behavior, tone, and structure by editing prompts instead of modifying application logic.

Scale AI Features Safely

Roll out improvements, A/B test variations, and manage risk through prompt versioning and controlled updates.

Connect AI to Business Context

Embed domain rules, policies, and structured outputs directly into prompts to align AI with business needs.

Create a Prompt

AI Studio
API & SDK

Navigate to a Project

Open a Project and click the + button at the top.

Select Prompt

Choose Prompt from the menu. The Prompt editor opens in AI Studio.

Standalone prompts are stored in the Project and can be reused across Playgrounds, Experiments, Agents, and Deployments.

Create a Prompt using the Create a Prompt API. The payload defines the name, model, messages, parameters, and metadata.

curl --request POST \
     --url https://api.orq.ai/v2/prompts \
     --header 'accept: application/json' \
     --header 'authorization: Bearer ORQ_API_KEY' \
     --header 'content-type: application/json' \
     --data '{
  "prompt_config": {
    "model_parameters": {
      "responseFormat": null,
      "temperature": 1,
      "maxTokens": 256,
      "topP": 0.7,
      "frequencyPenalty": 0,
      "presencePenalty": 0
    },
    "model": "openai/gpt-4o",
    "model_type": "vision",
    "provider": "openai",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant"
      }
    ]
  },
  "display_name": "MyPrompt",
  "path": "Default/Prompts",
  "metadata": {
    "language": "English"
  },
  "description": "Prompt Description"
}'

import { Orq } from "@orq-ai/node";

const orq = new Orq({
  apiKey: process.env["ORQ_API_KEY"] ?? "",
});

const result = await orq.prompts.create({
  displayName: "MyPrompt",
  promptConfig: {
    modelParameters: {
      responseFormat: null,
      temperature: 1,
      maxTokens: 256,
      topP: 0.7,
      frequencyPenalty: 0,
      presencePenalty: 0,
    },
    model: "openai/gpt-4o",
    modelType: "vision",
    provider: "openai",
    messages: [
      {
        role: "system",
        content: "You are a helpful assistant",
      },
    ],
  },
  path: "Default/Prompts",
  metadata: {
    language: "English",
  },
});

console.log(result);

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:
    res = orq.prompts.create(request={
        "display_name": "MyPrompt",
        "prompt_config": {
            "model_parameters": {
                "responseFormat": None,
                "temperature": 1,
                "maxTokens": 256,
                "topP": 0.7,
                "frequencyPenalty": 0,
                "presencePenalty": 0,
            },
            "model": "openai/gpt-4o",
            "model_type": "vision",
            "provider": "openai",
            "messages": [{
                "role": "system",
                "content": "You are a helpful assistant"
            }],
        },
        "path": "Default/Prompts",
        "metadata": {"language": "English"},
        "description": "Prompt Description",
    })

    print(res)

The response includes the prompt _id needed for future updates or retrieval.

See the full Create a Prompt API reference.

Choose a Model

AI Studio

Select a model from the model picker at the top of the Prompt editor.

A model must be available through the AI Gateway to appear in the picker.

Model Parameters

Temperature

Controls creativity and predictability. Higher values produce more diverse, surprising responses. Lower values produce more predictable output that sticks closely to learned patterns.

Max Tokens

Sets the upper limit on tokens the model can produce in a single output. Prevents excessively long responses while ensuring enough room for a complete answer.

Top K

Narrows the model’s choices to the k most likely tokens at each generation step. Helps refine output to follow particular patterns or meet specific criteria.

Top P

Nucleus sampling. Selects a pool of likely words based on a probability threshold, balancing creativity with coherence.

Frequency Penalty

Discourages the model from reusing the same words or phrases, encouraging richer and more varied language.

Presence Penalty

Discourages repeated topics or ideas rather than specific words. Higher values lead to more creative and diverse responses.

Messages

AI Studio

Select Add Message in the Prompt Template panel to add a message. Messages define the context the model receives before generating a response.

The prompt template used as context for the language model.

Roles

When adding a message, choose a role to define how the model interprets it:

Role	Description	Example
System	A guideline or context for the language model, directing how it should interpret and respond to requests.	”You are an expert botanist. Respond briefly to questions with one-line answers.”
User	An actual query posed by the user.	”Which plants thrive in shady environments?”
Assistant	Responses to user queries by the language model.	”Ferns, Hostas, and Hydrangeas are some plants that thrive in shady environments.”

Variables

AI Studio

Use {{variable_name}} syntax inside a message to declare a dynamic input. All declared inputs appear in the Inputs block at the top-right of the page, where default values can be set for testing.The example below shows the inputs being set while running the prompt in the Playground.

Inputs block in the Playground with a variable value being overridden while running a prompt. — Inputs being set and overridden while running a prompt in the Playground.

To pass values at runtime in a Deployment, see Variables and Prompt Templating.

Prompt Generator

AI Studio

Select the Generate Prompt button next to the Role Selector to open the prompt generation assistant.

The Generate Prompt button located next to the Role Selector in the prompt editor.

Select Copy to copy the generated prompt to the clipboard.
Select Apply to overwrite the current prompt with the generated one.

Fetch a Prompt

API & SDK

Retrieve a Prompt by its ID using the Retrieve a Prompt API.

curl --request GET \
     --url https://api.orq.ai/v2/prompts/PROMPT_ID \
     --header 'accept: application/json' \
     --header 'authorization: Bearer ORQ_API_KEY'

import { Orq } from "@orq-ai/node";

const orq = new Orq({
  apiKey: process.env["ORQ_API_KEY"] ?? "",
});

const result = await orq.prompts.retrieve({
  id: "<id>",
});

console.log(result);

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:
    res = orq.prompts.retrieve(id="<id>")
    print(res)

See the full Retrieve a Prompt API reference.

Get Started

AI Gateway

AI Observability

AI Engineering

AI Governance

AI Chat

Settings

Use Cases

Create a Prompt

Choose a Model

Model Parameters

Messages

Roles

Variables

Prompt Generator

Fetch a Prompt

​Use Cases

​Create a Prompt

​Choose a Model

​Model Parameters

​Messages

​Roles

​Variables

​Prompt Generator

​Fetch a Prompt

Use Cases

Create a Prompt

Choose a Model

Model Parameters

Messages

Roles

Variables

Prompt Generator

Fetch a Prompt