Skip to main content

Prompt Library

View all prompts, select an existing one, or create a new prompt from a centralized library.

Message Builder

Compose prompts using System and User messages for chat-style model interactions.

Variables + Inputs

Parameterize prompts with variables and provide runtime values using Fields or JSON.

Model Configuration

Configure the provider, model, and runtime parameters so behavior stays consistent across environments.

Publish Workflow

Publish immutable prompt versions with GitHub-style diffs and review changes before release.

Version History

Track all published versions along with metadata and change history.

Labels

Attach labels such as production, staging, or latest to control which version applications invoke.

Safe Iteration

Create drafts from existing prompt versions and iterate without modifying previously published versions.

When to Use Prompt Studio

Use Prompt Studio when you need a structured way to manage prompts across teams and environments, safely iterate on prompt changes, and control how updates are released to production systems.
SituationBenefit
You want a single place to manage prompts across services and teamsCentralized prompt management
You need controlled releases (dev → staging → production) without redeploying codeSafe production rollouts
You want an audit trail of prompt changesVersion diffs, comments, and history
You want to reproduce outcomes exactlyPin prompt versions and model settings

Step by step guide to manage your prompts

1

Create a Prompt

Open Prompt Studio and click Create Prompt to start a new prompt.
2

Add Messages

Compose your prompt using System and User messages.
  • System messages define role, rules, and guardrails.
  • User messages contain the request template and runtime input.
3

Define Variables

Add variables for dynamic inputs such as user messages, context, or knowledge snippets.Reference variables using placeholders like:{{user_message}}
4

Provide Inputs

Specify how variable values are provided at runtime.
MethodDescription
FieldsStructured inputs with name, type, and example values
JSONRuntime JSON payload for programmatic invocation
5

Configure the Model

Select the provider, model, and runtime parameters that control how the prompt executes.
SettingDescription
ProviderThe model provider used to run the prompt (for example, OpenAI)
ModelThe specific model that will generate responses
TemperatureControls randomness in the output
Max tokensLimits the maximum length of the response
Top PAdjusts sampling diversity when generating text
Keep temperature low for deterministic tasks such as support replies, extraction, or formatting. Increase it when creativity is needed.
6

Publish the Prompt

Click Publish to convert the draft into an immutable version.You can review the change, add a comment, and assign labels.
7

Manage Versions

Use Version History and labels (production, or any custom label) to control which prompt version your application invokes.

Immutability and Iteration

Published prompt versions are immutable, meaning they cannot be edited after they are published. This ensures that production behavior remains predictable and that every version can be audited or reproduced later. When you need to update a prompt, you create a new draft, make your changes, and publish a new version.
1

Create a New Draft

Select any published version and create a draft from it.
The draft acts as a working copy where changes can be made safely.
2

Edit and Iterate

Modify messages, variables, or model settings in the draft.
You can iterate and test freely without affecting the currently published version.
3

Publish a New Version

When your changes are ready, click Publish to create a new immutable version.
You can then assign labels such as staging or production to control which version is used.

Best Practices

PracticeWhy It Matters
Treat prompts like APIsStable inputs and predictable outputs
Write publish comments like changelogsImproves traceability and collaboration
Use labels as release channelsManage deployments safely (dev → staging → production)
Keep prompts focusedCompose multiple prompts instead of one large prompt
Write clear publish commentsHelps teammates quickly understand what changed
Keep changes small and descriptiveMakes it easier to track who changed what and why

FAQ

Published versions are immutable. To make changes, create a new draft from a published version, update it, and publish a new version.
Move the production label to the version you want your application to use.
Last modified on March 6, 2026