Melhorar um prompt
Criar um prompt novo e aprimorado guiado por feedback
As APIs de ferramentas de prompt estão em uma prévia de pesquisa fechada. Solicite para participar da prévia de pesquisa fechada.
Antes de começar
As ferramentas de prompt são um conjunto de APIs para gerar e melhorar prompts. Diferentemente de nossas outras APIs, esta é uma API experimental: você precisará solicitar acesso, e ela não tem o mesmo nível de compromisso com suporte a longo prazo como outras APIs.
Essas APIs são similares ao que está disponível no Anthropic Workbench, e são destinadas para uso por outras plataformas de engenharia de prompt e playgrounds.
Começando com o aprimorador de prompt
Para usar a API de geração de prompt, você precisará:
- Ter se juntado à prévia de pesquisa fechada para as APIs de ferramentas de prompt
- Usar a API diretamente, em vez do SDK
- Adicionar o cabeçalho beta
prompt-tools-2025-04-02
Esta API não está disponível no SDK
Melhorar um prompt
Headers
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.
Body
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.
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.
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.
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"
1 - 256
Response
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.
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.
Usage information
Was this page helpful?