> ## Documentation Index
> Fetch the complete documentation index at: https://www.adaline.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Deploy your prompt

> Ship your prompts from Adaline to your AI applications in real time

Deploying a prompt makes it available to your AI applications via the Adaline API or SDK. You can deploy directly to any deployment environment — and promote prompts across environments as they progress through your pipeline.

## Deploy to an environment

The deployment environment view is the central space for managing deployments. It is divided into three zones:

![Deployment environment view in Adaline](https://mintcdn.com/adaline/6qZ1-Sm8NeEttI_w/images/deploy/deploy-from-environment.gif?s=0773a690137d175c5016e18d5b786a8c)

> [!NOTE]
>
> The banner at the bottom shows the deployment direction (e.g., **Editor -> Production**). This is a visual indicator of what you are about to deploy — it is not clickable.

| Zone | What it shows |
| - | - |
| **Left** | Deployment history — all previously deployed prompt versions across environments. From here you can [rollback](https://www.adaline.ai/docs/deploy/rollback-your-prompt.md) to any previous version. |
| **Center** | The diff view — blue-highlighted content shows what will change when you deploy. This includes changes to `config` (model and settings), `messages`, `role`, `modality` (text, image, PDF), and `tools`. |
| **Right** | Environment selector, [webhooks](https://www.adaline.ai/docs/deploy/configure-webhooks.md), and API/SDK integration code for the deployed prompt. |

### Confirm the deployment

When you are ready, click **Deploy** to push the prompt to the selected environment:

![Confirming a deployment in Adaline](https://mintcdn.com/adaline/tvqUtfKxTlDfJpNv/images/deploy/actual-deployment.png?fit=max\&auto=format\&n=tvqUtfKxTlDfJpNv\&q=85\&s=c57cf2d373eba789cce90e1424f1d23b)

After deployment completes, Adaline shows the deployed state:

![Completed deployment in Adaline](https://mintcdn.com/adaline/Um_T8BffW4hfcoYD/images/deploy/deployment-done.png?fit=max\&auto=format\&n=Um_T8BffW4hfcoYD\&q=85\&s=7bdfdb49204a4973dfb0965d384d24fd)

The right panel now displays:

* **Integration IDs** — Deployment snapshot ID, environment ID, and prompt bench ID for use in your API/SDK calls. Adaline auto-fills the code snippets in the **API Integration** section.
* **Webhook executions** — Status of any [webhook](https://www.adaline.ai/docs/deploy/configure-webhooks.md) deliveries triggered by the deployment.

## Deploy to another environment

To promote a prompt from one environment to another (e.g., staging to production), select the prompt and click **Deploy to...**:

![Deploying to another environment](https://mintcdn.com/adaline/tvqUtfKxTlDfJpNv/images/deploy/change-deployment-environment.png?fit=max\&auto=format\&n=tvqUtfKxTlDfJpNv\&q=85\&s=d9c60bedaaa4b67aaa26d1895ab03897)

This lets you move prompts forward or backward through your deployment pipeline. For example:

* **Staging -> Production** — Promote a tested prompt to your live application.
* **Production -> Staging** — Pull a production prompt back to staging for further testing or iteration.

> [!TIP]
>
> Before deploying to production, [compare the deployments](https://www.adaline.ai/docs/deploy/compare-your-deployments.md) between environments to review exactly what will change.

## Access deployed prompts

After deployment, your AI application can access the prompt via:

* **API** — Use the Adaline [REST API](https://www.adaline.ai/docs/reference/api/v2/openapi/get-deployment.md) with your environment key and deployment IDs.
* **SDK** — Use the [TypeScript](https://www.adaline.ai/docs/reference/sdk/v2/typescript/overview.md) or [Python](https://www.adaline.ai/docs/reference/sdk/v2/python/overview.md) SDK to fetch and execute deployed prompts.
* **Webhooks** — [Configure webhooks](https://www.adaline.ai/docs/deploy/configure-webhooks.md) to receive real-time notifications whenever a deployment is created or rolled back.

## What gets deployed

A deployment captures a complete snapshot of your prompt, including:

| Component | Description |
| - | - |
| **Config** | The selected model and all its parameter settings (temperature, max tokens, response format, etc.). |
| **Messages** | All message templates — system, user, assistant, and tool messages. |
| **Variables** | All variable definitions and their configured sources. |
| **Tools** | Tool definitions, schemas, and request configurations. |
| **MCP servers** | Any connected MCP server configurations. |

Here is a sample deployment object returned by the [API](https://www.adaline.ai/docs/reference/api/v2/openapi/get-deployment.md) and [SDK](https://www.adaline.ai/docs/reference/sdk/v2/typescript/types/deployment.md):

```json theme={null}
{
  "id": "deploy_abc123",
  "createdAt": 1704067200000,
  "updatedAt": 1704153600000,
  "projectId": "proj_789",
  "promptId": "prompt_abc123",
  "deploymentEnvironmentId": "env_production",
  "prompt": {
    "config": {
      "providerName": "openai",
      "providerId": "provider_abc123",
      "model": "gpt-4o",
      "settings": {
        "temperature": 0.7,
        "maxTokens": 1000,
        "topP": 0.9
      }
    },
    "messages": [
      {
        "role": "system",
        "content": [
          {
            "modality": "text",
            "value": "You are a helpful customer support agent for {{company_name}}. Answer questions about our products and services."
          }
        ]
      },
      {
        "role": "user",
        "content": [
          {
            "modality": "text",
            "value": "{{user_message}}"
          }
        ]
      }
    ],
    "tools": [
      {
        "type": "function",
        "definition": {
          "schema": {
            "name": "search_knowledge_base",
            "description": "Search the company knowledge base for relevant articles",
            "parameters": {
              "type": "object",
              "properties": {
                "query": {
                  "type": "string",
                  "description": "The search query"
                }
              },
              "required": ["query"]
            }
          }
        }
      }
    ],
    "variables": [
      { "name": "company_name", "modality": "text" },
      { "name": "user_message", "modality": "text" }
    ]
  }
}
```

> [!TIP]
>
> Deployments return prompt messages with `{{variable_name}}` placeholders intact. Replace them with runtime values before sending to your AI provider — see [Use variables in a prompt](https://www.adaline.ai/docs/iterate/use-variables-in-prompt.md#injecting-variables-at-runtime) for the pattern in TypeScript and Python.

## Next steps

> [card] [Rollback Your Prompt](https://www.adaline.ai/docs/deploy/rollback-your-prompt.md)
>
> Revert to a previous deployment instantly.

> [card] [Compare Your Deployments](https://www.adaline.ai/docs/deploy/compare-your-deployments.md)
>
> Review diffs between deployment versions.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.