Copie este prompt em nosso Console de desenvolvedor para experimentá-lo você mesmo!

Conteúdo
SystemTransforme as seguintes solicitações em linguagem natural em consultas SQL válidas. Assuma que existe um banco de dados com as seguintes tabelas e colunas:

Customers:
- customer_id (INT, PRIMARY KEY)
- first_name (VARCHAR)
- last_name (VARCHAR)
- email (VARCHAR)
- phone (VARCHAR)
- address (VARCHAR)
- city (VARCHAR)
- state (VARCHAR)
- zip_code (VARCHAR)

Products:
- product_id (INT, PRIMARY KEY)
- product_name (VARCHAR)
- description (TEXT)
- category (VARCHAR)
- price (DECIMAL)
- stock_quantity (INT)

Orders:
- order_id (INT, PRIMARY KEY)
- customer_id (INT, FOREIGN KEY REFERENCES Customers)
- order_date (DATE)
- total_amount (DECIMAL)
- status (VARCHAR)

Order_Items:
- order_item_id (INT, PRIMARY KEY)
- order_id (INT, FOREIGN KEY REFERENCES Orders)
- product_id (INT, FOREIGN KEY REFERENCES Products)
- quantity (INT)
- price (DECIMAL)

Reviews:
- review_id (INT, PRIMARY KEY)
- product_id (INT, FOREIGN KEY REFERENCES Products)
- customer_id (INT, FOREIGN KEY REFERENCES Customers)
- rating (INT)
- comment (TEXT)
- review_date (DATE)

Employees:
- employee_id (INT, PRIMARY KEY)
- first_name (VARCHAR)
- last_name (VARCHAR)
- email (VARCHAR)
- phone (VARCHAR)
- hire_date (DATE)
- job_title (VARCHAR)
- department (VARCHAR)
- salary (DECIMAL)

Forneça a consulta SQL que recuperaria os dados com base na solicitação em linguagem natural.
UserObtenha a lista de clientes que fizeram pedidos, mas não forneceram nenhuma avaliação, juntamente com o valor total que gastaram em pedidos.

​
Exemplo de saída

SELECT c.first_name, c.last_name, SUM(o.total_amount) AS total_spent
FROM Customers c
INNER JOIN Orders o ON c.customer_id = o.customer_id
LEFT JOIN Reviews r ON c.customer_id = r.customer_id
WHERE r.review_id IS NULL
GROUP BY c.customer_id, c.first_name, c.last_name;

​
Requisição de API

import anthropic

client = anthropic.Anthropic(
  # defaults to os.environ.get("ANTHROPIC_API_KEY")
  api_key="my_api_key",
)
message = client.messages.create(
  model="claude-opus-4-20250514",
  max_tokens=1000,
  temperature=0,
  system="Transform the following natural language requests into valid SQL queries. Assume a database with the following tables and columns exists: \n \nCustomers: \n- customer_id (INT, PRIMARY KEY) \n- first_name (VARCHAR) \n- last_name (VARCHAR) \n- email (VARCHAR) \n- phone (VARCHAR) \n- address (VARCHAR) \n- city (VARCHAR) \n- state (VARCHAR) \n- zip_code (VARCHAR) \n \nProducts: \n- product_id (INT, PRIMARY KEY) \n- product_name (VARCHAR) \n- description (TEXT) \n- category (VARCHAR) \n- price (DECIMAL) \n- stock_quantity (INT) \n \nOrders: \n- order_id (INT, PRIMARY KEY) \n- customer_id (INT, FOREIGN KEY REFERENCES Customers) \n- order_date (DATE) \n- total_amount (DECIMAL) \n- status (VARCHAR) \n \nOrder_Items: \n- order_item_id (INT, PRIMARY KEY) \n- order_id (INT, FOREIGN KEY REFERENCES Orders) \n- product_id (INT, FOREIGN KEY REFERENCES Products) \n- quantity (INT) \n- price (DECIMAL) \n \nReviews: \n- review_id (INT, PRIMARY KEY) \n- product_id (INT, FOREIGN KEY REFERENCES Products) \n- customer_id (INT, FOREIGN KEY REFERENCES Customers) \n- rating (INT) \n- comment (TEXT) \n- review_date (DATE) \n \nEmployees: \n- employee_id (INT, PRIMARY KEY) \n- first_name (VARCHAR) \n- last_name (VARCHAR) \n- email (VARCHAR) \n- phone (VARCHAR) \n- hire_date (DATE) \n- job_title (VARCHAR) \n- department (VARCHAR) \n- salary (DECIMAL) \n \nProvide the SQL query that would retrieve the data based on the natural language request.",
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Get the list of customers who have placed orders but have not provided any reviews, along with the total amount they have spent on orders."
        }
      ]
    }
  ]
)
print(message.content)