POST
/
v1
/
experimental
/
improve_prompt
curl -X POST https://api.anthropic.com/v1/experimental/improve_prompt \
     --header "x-api-key: $ANTHROPIC_API_KEY" \
     --header "anthropic-version: 2023-06-01" \
     --header "anthropic-beta: prompt-tools-2025-04-02" \
     --header "content-type: application/json" \
     --data \
'{
    "messages": [{"role": "user", "content": [{"type": "text", "text": "Create a recipe for {{food}}"}]}],
    "system": "You are a professional chef",
    "feedback": "Make it more detailed and include cooking times",
    "target_model": "claude-3-7-sonnet-20250219"
}'
{
  "messages": [
    {
      "content": [
        {
          "text": "<improved prompt>",
          "type": "text"
        }
      ],
      "role": "user"
    },
    {
      "content": [
        {
          "text": "<assistant prefill>",
          "type": "text"
        }
      ],
      "role": "assistant"
    }
  ],
  "system": "",
  "usage": [
    {
      "input_tokens": 490,
      "output_tokens": 661
    }
  ]
}

프롬프트 도구 API는 비공개 연구 미리보기 단계에 있습니다. 비공개 연구 미리보기 참여 요청.

​
시작하기 전에

프롬프트 도구는 프롬프트를 생성하고 개선하는 API 세트입니다. 다른 API와 달리, 이것은 실험적 API입니다: 액세스를 요청해야 하며, 다른 API와 같은 수준의 장기 지원 약속이 없습니다.

이러한 API는 Anthropic Workbench에서 사용할 수 있는 것과 유사하며, 다른 프롬프트 엔지니어링 플랫폼과 플레이그라운드에서 사용하기 위한 것입니다.

​
프롬프트 개선기 시작하기

프롬프트 생성 API를 사용하려면 다음이 필요합니다:

  1. 프롬프트 도구 API의 비공개 연구 미리보기에 참여했을 것
  2. SDK가 아닌 API를 직접 사용할 것
  3. 베타 헤더 prompt-tools-2025-04-02 추가할 것

이 API는 SDK에서 사용할 수 없습니다

​
프롬프트 개선하기

Headers

​
anthropic-beta
string[]

Optional header to specify the beta version(s) you want to use.

To use multiple betas, use a comma separated list like beta1,beta2 or specify the header multiple times for each beta.

​
x-api-key
string
required

Your unique API key for authentication.

This key is required in the header of all API requests, to authenticate your account and access Anthropic's services. Get your API key through the Console. Each key is scoped to a Workspace.

Body

application/json
​
messages
object[]
required

The prompt to improve, structured as a list of message objects.

Each message in the messages array must:

  • Contain only text-only content blocks
  • Not include tool calls, images, or prompt caching blocks

As a simple text prompt:

[
  {
    "role": "user", 
    "content": [
      {
        "type": "text",
        "text": "Concise recipe for {{food}}"
      }
    ]
  }
]

With example interactions to guide improvement:

[
  {
    "role": "user", 
    "content": [
      {
        "type": "text",
        "text": "Concise for {{food}}.\n\nexample\mandu: Put the mandu in the air fryer at 380F for 7 minutes."
      }
    ]
  }
]

Note that only contiguous user messages with text content are allowed. Assistant prefill is permitted, but other content types will cause validation errors.

Examples:
[
  {
    "content": [
      {
        "text": "<generated prompt>",
        "type": "text"
      }
    ],
    "role": "user"
  }
]
​
feedback
string | null

Feedback for improving the prompt.

Use this parameter to share specific guidance on what aspects of the prompt should be enhanced or modified.

Example:

{
  "messages": [...],
  "feedback": "Make the recipes shorter"
}

When not set, the API will improve the prompt using general prompt engineering best practices.

Examples:

"Make it more detailed and include cooking times"

​
system
string | null

The existing system prompt to incorporate, if any.

{
  "system": "You are a professional meal prep chef",
  [...]
}

Note that while system prompts typically appear as separate parameters in standard API calls, in the improve_prompt response, the system content will be incorporated directly into the returned user message.

Examples:

"You are a professional chef"

​
target_model
string | null
default:

The model this prompt will be used for. This optional parameter helps us understand which models our prompt tools are being used with, but it doesn't currently affect functionality.

Example:

"claude-3-7-sonnet-20250219"
Required string length: 1 - 256
Examples:

"claude-3-7-sonnet-20250219"

Response

200
application/json
Successful Response
​
messages
object[]
required

Contains the result of the prompt improvement process in a list of message objects.

Includes a user-role message with the improved prompt text and may optionally include an assistant-role message with a prefill. These messages follow the standard Messages API format and can be used directly in subsequent API calls.

Examples:
[
  {
    "content": [
      {
        "text": "<improved prompt>",
        "type": "text"
      }
    ],
    "role": "user"
  },
  {
    "content": [
      {
        "text": "<assistant prefill>",
        "type": "text"
      }
    ],
    "role": "assistant"
  }
]
​
system
string
required

Currently, the system field is always returned as an empty string (""). In future iterations, this field may contain generated system prompts.

Directions similar to what would normally be included in a system prompt are included in messages when improving a prompt.

Examples:

""

​
usage
object
required

Usage information