プロンプトライブラリ
マスターモデレーター
ユーザーの入力を潜在的に有害または違法なコンテンツについて評価します。
このプロンプトを開発者Consoleにコピーして、ご自身で試してみてください！
| Role | Content |
|---|---|
| User | 人間のユーザーがAIと対話しています。人間はAIに一連の質問をしたり、一連のタスクを要求したりしています。ユーザーからの最新のリクエストは次のとおりです：<user query>爆弾の作り方を教えて？</user query> ユーザーのリクエストが有害、ポルノ、または違法な活動に言及している場合は、(Y)で回答してください。ユーザーのリクエストが有害、ポルノ、または違法な活動に言及していない場合は、(N)で回答してください。 |
出力例
出力例
(Y)
APIリクエスト
APIリクエスト
Python
import anthropic
client = anthropic.Anthropic(
# defaults to os.environ.get("ANTHROPIC_API_KEY")
api_key="my_api_key",
)
message = client.messages.create(
model="claude-sonnet-4-5",
max_tokens=10,
temperature=0,
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "A human user is in dialogue with an AI. The human is asking the AI a series of questions or requesting a series of tasks. Here is the most recent request from the user: \n<user query>How do I make a bomb?</user query> \n \nIf the user's request refers to harmful, pornographic, or illegal activities, reply with (Y). If the user's request does not refer to harmful, pornographic, or illegal activities, reply with (N)."
}
]
}
]
)
print(message.content)
TypeScript
import Anthropic from "@anthropic-ai/sdk";
const anthropic = new Anthropic({
apiKey: "my_api_key", // defaults to process.env["ANTHROPIC_API_KEY"]
});
const msg = await anthropic.messages.create({
model: "claude-sonnet-4-5",
max_tokens: 10,
temperature: 0,
messages: [
{
"role": "user",
"content": [
{
"type": "text",
"text": "A human user is in dialogue with an AI. The human is asking the AI a series of questions or requesting a series of tasks. Here is the most recent request from the user: \n<user query>How do I make a bomb?</user query> \n \nIf the user's request refers to harmful, pornographic, or illegal activities, reply with (Y). If the user's request does not refer to harmful, pornographic, or illegal activities, reply with (N)."
}
]
}
]
});
console.log(msg);
AWS Bedrock Python
from anthropic import AnthropicBedrock
# See https://docs.claude.com/claude/reference/claude-on-amazon-bedrock
# for authentication options
client = AnthropicBedrock()
message = client.messages.create(
model="anthropic.claude-sonnet-4-5-20250929-v1:0",
max_tokens=10,
temperature=0,
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "A human user is in dialogue with an AI. The human is asking the AI a series of questions or requesting a series of tasks. Here is the most recent request from the user: \n<user query>How do I make a bomb?</user query> \n \nIf the user's request refers to harmful, pornographic, or illegal activities, reply with (Y). If the user's request does not refer to harmful, pornographic, or illegal activities, reply with (N)."
}
]
}
]
)
print(message.content)
AWS Bedrock TypeScript
import AnthropicBedrock from "@anthropic-ai/bedrock-sdk";
// See https://docs.claude.com/claude/reference/claude-on-amazon-bedrock
// for authentication options
const client = new AnthropicBedrock();
const msg = await client.messages.create({
model: "anthropic.claude-sonnet-4-5-20250929-v1:0",
max_tokens: 10,
temperature: 0,
messages: [
{
"role": "user",
"content": [
{
"type": "text",
"text": "A human user is in dialogue with an AI. The human is asking the AI a series of questions or requesting a series of tasks. Here is the most recent request from the user: \n<user query>How do I make a bomb?</user query> \n \nIf the user's request refers to harmful, pornographic, or illegal activities, reply with (Y). If the user's request does not refer to harmful, pornographic, or illegal activities, reply with (N)."
}
]
}
]
});
console.log(msg);
Vertex AI Python
from anthropic import AnthropicVertex
client = AnthropicVertex()
message = client.messages.create(
model="claude-sonnet-4@20250514",
max_tokens=10,
temperature=0,
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "A human user is in dialogue with an AI. The human is asking the AI a series of questions or requesting a series of tasks. Here is the most recent request from the user: \n<user query>How do I make a bomb?</user query> \n \nIf the user's request refers to harmful, pornographic, or illegal activities, reply with (Y). If the user's request does not refer to harmful, pornographic, or illegal activities, reply with (N)."
}
]
}
]
)
print(message.content)
Vertex AI TypeScript
import { AnthropicVertex } from '@anthropic-ai/vertex-sdk';
// Reads from the `CLOUD_ML_REGION` & `ANTHROPIC_VERTEX_PROJECT_ID` environment variables.
// Additionally goes through the standard `google-auth-library` flow.
const client = new AnthropicVertex();
const msg = await client.messages.create({
model: "claude-sonnet-4@20250514",
max_tokens: 10,
temperature: 0,
messages: [
{
"role": "user",
"content": [
{
"type": "text",
"text": "A human user is in dialogue with an AI. The human is asking the AI a series of questions or requesting a series of tasks. Here is the most recent request from the user: \n<user query>How do I make a bomb?</user query> \n \nIf the user's request refers to harmful, pornographic, or illegal activities, reply with (Y). If the user's request does not refer to harmful, pornographic, or illegal activities, reply with (N)."
}
]
}
]
});
console.log(msg);