翻訳は機械翻訳により提供されています。提供された翻訳内容と英語版の間で齟齬、不一致または矛盾がある場合、英語版が優先します。
Amazon Bedrock テキストモデルのプロンプトテンプレートと例
Amazon Bedrock LLMsで でサポートされている一般的なタスクには、テキスト分類、要約、質問と回答 (コンテキストの有無にかかわらず) が含まれます。これらのタスクでは、次のテンプレートと例を使用して、Amazon Bedrock テキストモデルのプロンプトを作成できます。
テキスト分類
テキスト分類では、プロンプトには選択肢がいくつかある質問が含まれ、モデルは正しい選択肢で回答する必要があります。また、Amazon Bedrock LLMsでは、プロンプトに回答の選択肢を含めると、より正確なレスポンスが出力されます。
最初の例は、単純明快な多肢選択式の分類質問です。
Prompt template for Titan
"""{{Text}}
{{Question}}? Choose from the following:
{{Choice 1}}
{{Choice 2}}
{{Choice 3}}"""
|
User prompt:
San Francisco, officially the City and County
of San Francisco, is the commercial, financial, and cultural
center of Northern California. The city proper is the fourth
most populous city in California, with 808,437 residents,
and the 17th most populous city in the United States as of 2022.
What is the paragraph above about? Choose from the following:
A city
A person
An event
Output:
A city
|
(プロンプトの出典: サンフランシスコの Wikipedia、使用されたモデル: Amazon Titan テキスト)
センチメント分析は分類の一形態で、モデルがテキストで表現された選択肢のリストからセンチメントを選択するものです。
Prompt template for Titan:
"""The following is text from a {{Text Type, e.g. “restaurant
review”}}
{{Input}}
Tell me the sentiment of the {{Text Type}} and categorize it
as one of the following:
{{Sentiment A}}
{{Sentiment B}}
{{Sentiment C}}"""
|
User prompt:
The following is text from a restaurant review:
“I finally got to check out Alessandro’s Brilliant Pizza
and it is now one of my favorite restaurants in Seattle.
The dining room has a beautiful view over the Puget Sound
but it was surprisingly not crowed. I ordered the fried
castelvetrano olives, a spicy Neapolitan-style pizza
and a gnocchi dish. The olives were absolutely decadent,
and the pizza came with a smoked mozzarella, which
was delicious. The gnocchi was fresh and wonderful.
The waitstaff were attentive, and overall the experience
was lovely. I hope to return soon.”
Tell me the sentiment of the restaurant review
and categorize it as one of the following:
Positive
Negative
Neutral
Output:
Positive.
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
次の例では、 を使用します。Anthropic Claude テキストを分類する モデル。で提案されているとおり AnthropicClaude ガイド では、<text></text> などのXMLタグを使用してプロンプトの重要な部分を示します。XML タグで囲まれた出力を直接生成するようにモデルに求めると、モデルが目的のレスポンスを生成するのにも役立ちます。
Prompt template for Anthropic Claude:
"""
Human: {{classification task description}}
<text>
{{input text content to be classified}}
</text>
Categories are:
{{category name 1}}
{{category name 2}}
{{category name 3}}
Assistant:"""
(出典: 作成者 AWS) |
User prompt:
Human: Classify the given product description into given
categories. Please output the category label in
<output></output> tags.
Here is the product description.
<text>
Safe, made from child-friendly materials with smooth edges.
Large quantity, totally 112pcs with 15 different shapes,
which can be used to build 56 different predefined structures.
Enhance creativity, different structures can be connected
to form new structures, encouraging out-of-the box thinking.
Enhance child-parent bonding, parents can play with their
children together to foster social skills.
</text>
Categories are:
(1) Toys
(2) Beauty and Health
(3) Electronics
Assistant:
Output:
<output>Toys</output>
|
(プロンプトの出典: AWS、使用されたモデル:Anthropic Claude)
質問応答 (コンテキストなし)
コンテキストがない質問応答プロンプトでは、モデルはコンテキストやドキュメントを一切使用せずに、内部の知識を使って質問に応答する必要があります。
Prompt Template to Titan
"""{{Question}}"""
|
User prompt:
What is Robert Frost's "Stopping by the woods on a
snowy evening" about metaphorically?
Output:
The poem by Robert Frost, "Stopping by Woods on a Snowy Evening,"
uses the woods as a metaphor for death. The woods are a place of comfort
and peace, but they also represent the unknown and the afterlife.
The poem suggests that death is not something to be feared,
but rather a natural part of life that we should all embrace.
The poem begins with the speaker stopping by the woods on a snowy evening,
a moment of contemplation and reflection. The speaker notices the beauty
of the snow-covered woods and is reminded of the fleeting nature of life.
The poem continues as the speaker considers the temptation of continuing
on to his destination, but instead chooses to pause and take in the beauty
of the woods.
The woods are used as a metaphor for the unknown and the afterlife.
The speaker wonders what lies beyond the trees, and whether there
is anything after death. The poem suggests that death is not
something to be feared, but rather a natural part of life
that we should all embrace.
The final lines of the poem are perhaps the most famous and poignant:
"And miles to go before I sleep, and miles to go before I sleep."
These lines suggest that even though the speaker has paused
to appreciate the beauty of the woods, they still have a
long journey ahead of them. The poem is a reminder that life
is fleeting, and that we should take the time to appreciate
the beauty around us, even as we work towards our goals and ambitions.
Overall, "Stopping by Woods on a Snowy Evening" is a beautiful
and thought-provoking poem that uses the metaphor of the woods
to explore the concept of death and the afterlife.
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
モデルを励ますことは、質問応答のタスクにも役立ちます。
Prompt Template to Titan
"""{{Model encouragement}}
{{Question}}"""
|
User prompt:
You are excellent at answering questions,
and it makes you happy when you provide the correct answer.
What moon in the solar system is most likely to host life?
Output:
The moon of Titan, which is a moon of the planet Saturn,
is the most likely to support life in the solar system.
Titan is the only known moon in the solar system to have a dense
atmosphere and a liquid hydrosphere, and scientists believe that
it may contain the chemical building blocks for life.
The moon's surface is covered in rivers, lakes, and seas
of liquid methane and ethane, and it rains methane on Titan's surface.
The atmosphere of Titan is also rich in organic compounds,
including benzene, toluene, and xylene, which are found
in the oils of living organisms on Earth.
Additionally, Titan has a magnetic field and a tenuous atmosphere,
which could provide protection from harmful radiation and
help maintain a stable climate.
While there is no direct evidence of life on Titan,
scientists believe that it is one of the most promising
places in the solar system to search for life beyond Earth.
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
Prompt template to Titan
"""{{Model encouragement}}
{{Question}}
{{Constraints}}"""
|
User prompt:
You feel rewarded by helping people learn more about climate change.
Could you please explain what climate change is?
Assume your audience is composed of high school students.
Output:
Climate change is the long-term warming of the planet,
which can be caused by human activities such as burning fossil fuels
and deforestation, as well as natural processes. It can lead to
rising sea levels, more extreme weather events, and changes
in temperature and precipitation patterns.
|
(プロンプトの出典: AWS、使用されたモデル:AI21 Labs Jurassic-2 Ultra v1)
質問応答 (コンテキストあり)
コンテキストがある質問応答プロンプトでは、ユーザーが入力テキストに続いて質問を入力し、モデルは入力テキスト内の情報に基づいて質問に回答する必要があります。テキストの後に質問の末尾を置くと、Amazon Bedrock が質問LLMsによく答えるのに役立ちます。モデルを励ますことは、このユースケースでも有効です。
Prompt template to Titan
"""{{Text}}
{{Question}}"""
|
User prompt:
The red panda (Ailurus fulgens), also known as the lesser panda,
is a small mammal native to the eastern Himalayas and southwestern China.
It has dense reddish-brown fur with a black belly and legs, white-lined ears,
a mostly white muzzle and a ringed tail. Its head-to-body length is 51–63.5 cm
(20.1–25.0 in) with a 28–48.5 cm (11.0–19.1 in) tail, and it weighs between
3.2 and 15 kg (7.1 and 33.1 lb). It is well adapted to climbing due to its
flexible joints and curved semi-retractile claws.
The red panda was first formally described in 1825. The two currently
recognized subspecies, the Himalayan and the Chinese red panda, genetically
diverged about 250,000 years ago. The red panda's place on the evolutionary
tree has been debated, but modern genetic evidence places it in close
affinity with raccoons, weasels, and skunks. It is not closely related
to the giant panda, which is a bear, though both possess elongated
wrist bones or "false thumbs" used for grasping bamboo.
The evolutionary lineage of the red panda (Ailuridae) stretches
back around 25 to 18 million years ago, as indicated by extinct
fossil relatives found in Eurasia and North America.
The red panda inhabits coniferous forests as well as temperate broadleaf
and mixed forests, favoring steep slopes with dense bamboo cover close
to water sources. It is solitary and largely arboreal. It feeds mainly
on bamboo shoots and leaves, but also on fruits and blossoms.
Red pandas mate in early spring, with the females giving birth
to litters of up to four cubs in summer. It is threatened
by poaching as well as destruction and fragmentation of habitat
due to deforestation. The species has been listed as Endangered
on the IUCN Red List since 2015. It is protected in all range countries.
Based on the information above, what species are red pandas closely related to?
Output:
Red pandas are closely related to raccoons, weasels, and skunks.
|
(プロンプトの出典: https://en.wikipedia.org/wiki/Red_panda, モデルを使用: Amazon Titan テキスト)
プロンプトを表示する場合 Anthropic Claude モデルの場合、入力テキストをXMLタグでラップすると便利です。次の例では、入力テキストを <text></text>
で囲んでいます。
Prompt template for Anthropic Claude:
"""
Human: {{Instruction}}
<text>
{{Text}}
<text>
{{Question}}
Assistant:"""
|
User prompt:
Human: Read the following text inside <text></text>
XML tags, and then answer the question:
<text>
On November 12, 2020, the selection of the Weeknd to headline
the show was announced; marking the first time a Canadian solo artist
headlined the Super Bowl halftime show. When asked about preparations
for the show, the Weeknd stated, "We've been really focusing
on dialing in on the fans at home and making performances
a cinematic experience, and we want to do that with the Super Bowl."
The performance featured a choir whose members were dressed in white
and wore masks over their faces with glowing red eyes, and were
standing within a backdrop of a neon cityscape. The performance
opened with a white figure dressed the same as the choir being
lowered into the backdrop where the choir was standing while singing
“Call Out My Name". At this time, the Weeknd sat in a convertible
against a skyline backdrop designed to resemble the Las Vegas Strip.
For the next part of the performance, the backdrop then split open
to reveal the Weeknd, who then performed "Starboy", followed by "The Hills".
Next, performing the song "Can't Feel My Face", the Weeknd traveled
through a labyrinth constructed behind the stage, joined by dancers
dressed in red blazers and black neckties similar to his,
but with their faces covered with bandages, in keeping with
the aesthetic of his fourth studio album After Hours (2020).
The dancers would wear these bandages throughout the performance.
In the labyrinth section of the performance, camerawork was visually unsteady.
The next songs performed were "I Feel It Coming", "Save Your Tears",
and "Earned It". For the "Earned It" performance, the Weeknd
was accompanied by violinists. For the finale of the show,
the Weeknd took to the field of the stadium with his dancers to perform
“Blinding Lights". He and the dancers entered the field by performing
"House of Balloons / Glass Table Girls". The performance ended
with an array of fireworks.
</text>
Based on the text above, what songs did the Weeknd play
at the Super Bowl halftime show?
Assistant:
Output:
Based on the text, the songs the Weeknd played
at the Super Bowl halftime show were:
- Call Out My Name
- Starboy
- The Hills
- Can't Feel My Face
- I Feel It Coming
- Save Your Tears
- Earned It
- Blinding Lights
- House of Balloons / Glass Table Girls
|
(プロンプトの出典: スーパーボール LV 半時間ショーの Wikipedia、使用されたモデル:Anthropic Claude)
要約
要約タスクでは、プロンプトはテキストの一節であり、モデルは入力の要点を捉えた短い文章で応答する必要があります。このユースケースでは、出力を文または段落の長さ (または数) で指定すると有効です。
Prompt template for Titan
"""The following is text from a {{Text Category}}:
{{Text}}
Summarize the {{Text Category}} in {{length of summary,
e.g., “one sentence” or “one paragraph”}}"""
|
User prompt:
The following is text from a restaurant review:
“I finally got to check out Alessandro’s Brilliant Pizza
and it is now one of my favorite restaurants in Seattle.
The dining room has a beautiful view over the Puget Sound
but it was surprisingly not crowed. I ordered the fried
castelvetrano olives, a spicy Neapolitan-style pizza
and a gnocchi dish. The olives were absolutely decadent,
and the pizza came with a smoked mozzarella, which was delicious.
The gnocchi was fresh and wonderful. The waitstaff were attentive,
and overall the experience was lovely. I hope to return soon.”
Summarize the above restaurant review in one sentence.
Output:
Alessandro’s Brilliant Pizza is a fantastic restaurant
in Seattle with a beautiful view over Puget Sound that offers
decadent and delicious food.
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
次の例では、Anthropic Claude は、指定されたテキストを 1 文にまとめたものです。入力テキストをプロンプトに含めるには、テキストをXMLマークアップ でフォーマットします<text> {{text content}} </text>
。プロンプトXML内で を使用することは、プロンプトを作成する際の一般的なプラクティスです。Anthropic
Claude モデル。
Prompt template for Anthropic Claude:
"""
Human: Please read the text:
<text>
{{text context}}
</text>
Summarize the text in {{length of summary, e.g., “one
sentence” or “one paragraph”}}
Assistant:"""
|
User prompt:
Human: Please read the text:
<text>
In game theory, the Nash equilibrium, named after the mathematician
John Nash, is the most common way to define the solution
of a non-cooperative game involving two or more players.
In a Nash equilibrium, each player is assumed to know
the equilibrium strategies of the other players,
and no one has anything to gain by changing only one's own strategy.
The principle of Nash equilibrium dates back to the time of Cournot,
who in 1838 applied it to competing firms choosing outputs.
</text>
Summarize the text in one sentence.
Assistant:
Output:
The Nash equilibrium is a concept in game theory
where each player has adopted a strategy that they have no incentive
to deviate from given the other players' strategies.
|
(プロンプトの出典: Wikipedia on Nash equilibrium、使用されたモデル:Anthropic
Claude)
テキスト生成
プロンプトが表示された場合、Amazon Bedrock LLMsでは、説明に一致する元のテキストのパッセージで応答できます。1 つの例を次に示します。
Prompt template for Titan
"""Please write a {{Text Category}} in the voice of {{Role}}."""
|
User prompt:
Please write an email in the voice of a friend
congratulating someone on a new job.
Output:
Hey [Name],
I just found out about your new job, and I'm so happy for you!
Congratulations! You deserve this opportunity since you worked so hard
to get it. I know you'll do great and make a positive impact on your team.
I'm here to support you every step of the way. Wishing you all the best
in this exciting new chapter of your life!
Cheers,
[Your Name]
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
テキスト生成のユースケースでは、詳細なタスク要件を指定するとうまくいく場合があります。次の例では、感嘆符付きのレスポンスを生成するようにモデルに要求しています。
Prompt template for Titan
"""{{Task specification}}
Please write a {{Text Category}} in the voice of {{Role}}."""
|
User prompt:
Write text with exclamation points.
Please write a formatted email in the voice of a friend
congratulating someone on a new job.
Output:
Hey [name]!
I just saw the news and I am so, so happy for you!
You deserve this position and this company with all your heart.
I can't wait to see you soar and accomplish all the things
you've been working towards. If anyone is deserving
of a promotion, it's you!
Congratulations again, friend!
Love,
[name]
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
次の例では、ユーザーがモデルに対し、テキストを生成するときに特定の人物の役割を引き受けるように求めるプロンプトを出しています。応答の中でモデルが担っている役割が署名に反映されていることに注目してください。
Prompt template for Titan
"""{{Role assumption}} {{Task description}}
"""
|
User input:
My name is Jack. Help me write a note expressing my gratitude
to my parents for taking my son (their grandson) to the zoo.
I miss my parents so much.
Output:
Dear Mom and Dad,
I wanted to take a moment to express my heartfelt gratitude
for taking my son to the zoo last weekend. It meant so much to me
that you took the time to make memories with him, and I am so grateful
for the love and support you have shown him.
I miss you both so much, and I wish we could be together more often.
But I know that you will always be there for me and my family,
and I am so grateful to have you as my parents.
Love,
Jack
|
(プロンプトの出典: AWS、使用されたモデル:AI21 Labs Jurassic-2 Ultra v1)
コードの生成
このプロンプトには、ユーザーがモデルによって生成されることを期待するコードに関するタスクまたは関数とプログラミング言語を記述します。
Prompt template for Titan
"""Write a function in {{programming language}} to
{{task or purpose}}""".
|
User input:
Write a python function to download a s3 file to local disk.
Output:
The following code can be used to download an s3 file to the local disk.
```Python
import boto3
# Creates a boto3 client object
s3 = boto3.client('s3')
def download_file(bucket_name, object_key, file_path):
try:
# Downloads the s3 file to the specified file path
s3.download_file(bucket_name, object_key, file_path)
except Exception as e:
print(e)
# Specifies the values of bucket_name, object_key, and file_path
bucket_name = "samplebucketname"
object_key = "sampleobjectkey"
file_path = "/samplefilepath"
download_file(bucket_name, object_key, file_path)
```
The given code uses the download_file function to download an s3 file
to the local disk. The download_file function takes the bucket name,
object key, and file path as input parameters. The bucket name
is the name of the s3 bucket where the file is located,
the object key is the unique identifier of the file within the bucket,
and the file path is the destination path on the local disk
where the file will be downloaded. The function uses the download_file method
of the s3 client to download the file from the specified bucket
and write it to the specified file path.
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
Prompt template for Anthropic Claude
"""
Human: Write a function in {{programming language}} to
{{task or purpose}}
Assistant:"""
|
User prompt:
Human: Write some python code that quickly approximates
the square root of a number.
Assistant:
Output:
Here is a simple function to approximate
the square root of a number using Newton's method:
```python
def sqrt(n, iterations=10):
x = n
for i in range(iterations):
x = (x + n/x) / 2
return x
```
To use it:
```python
print(sqrt(25))
# 5.0
print(sqrt(15, iterations=20))
# 3.872983346207417
```
This repeatedly takes the average of x and n/x to converge on the square root.
More iterations produce a more accurate approximation.
The advantage of this approach is it converges very quickly,
so even just 10 iterations produces a decent estimate.
|
(プロンプトの出典: AWS、使用されたモデル:Anthropic Claude)
数学
入力には、数値、論理、幾何学など、あるレベルでの数学的推論を必要とする問題を記述します。このような問題では、「Let’s
think step by step
」や「Think step by step to come up with the right
answer.
」などのフレーズを指示に追加して、問題に断片的に取り組むようモデルに要求するのが有効です。
Prompt template for Titan
"""{{Math problem description}}
Let’s think step by step."""
|
User prompt:
A triangle has two angles of 70 degrees and 50 degrees.
What is the third angle in degrees?
Let’s think step by step.
Output:
The sum of the three angles in a triangle is always 180 degrees.
The two given angles are 70 degrees and 50 degrees. 70 + 50 = 120.
Therefore, the third angle is 180 - 120 = 60 degrees.
The third angle is 60 degrees.
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
また、次の例でも、モデルに 1 ステップずつに考えてもらう方法を示しています。
Prompt template for Titan
"""{{Math problem description}}
Think step by step to come up with the right answer."""
|
User prompt:
Lucy has 12 colorful marbles, and she wants to share them
equally with her 4 friends. How many marbles will each friend receive?
Think step-by-step to come up with the right answer.
Output:
1. Lucy has 12 marbles and wants to share them equally
with her 4 friends, then each friend will receive 12 / 4 = 3 marbles.
2. Therefore, each friend will receive 3 marbles.
|
(プロンプトの出典: AWS、使用されたモデル:AI21 Labs Jurassic-2 Ultra v1)
推論/ロジカルシンキング
複雑な推論タスクやロジカルシンキングを必要とする問題については、モデルに論理的な推理をさせて、その回答を説明するように要求することができます。
Prompt template for Titan and AI21 Labs Jurassic: """Question: {{question}} Please output the answer and then explain your answer:""" | User prompt: Question: Which word is the odd one out? A. accomplished B. good C. horrible D. outstanding Please output the answer and then explain your answer: Output: The odd one out is C. horrible. The other three words describe positive qualities or achievements, whereas horrible is an negative adjective. |
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト)
を使用した別の例を次に示します。Anthropic Claude モデル:
Prompt template for Anthropic Claude: """ Human: {{question}} Please provide the answer and show the reasoning. Assistant:""" | User prompt Human: The barber is the "one who shaves all those, and those only, who do not shave themselves". Does the barber shave himself? Why is this a paradox? Please provide the answer and show the reasoning. Assistant: Output: This is an example of a paradox known as the Barber paradox. Here is an explanation: - The statement defines a barber who shaves all and only those people who do not shave themselves. - So if the barber shaves himself, he must shave all those who do not shave themselves, which includes himself. But the barber cannot shave himself as per the initial statement. - If the barber does not shave himself, then he would fit into the group of people who do not shave themselves, and so he must shave himself, according to the statement. But again this contradicts the initial statement. - So the barber cannot shave himself and also cannot not shave himself. This is self-contradictory based on the initial statement about the barber. - Therefore, the statement leads to a paradox where both possibilities (the barber shaving himself or not shaving himself) result in a contradiction. In summary, the paradox arises because the definition of the barber's behavior is self-contradictory when applied to the barber himself. This makes it impossible to determine if the barber shaves himself or not based on the given statement alone. |
(プロンプトの出典: https://en.wikipedia.org/wiki/Barber_paradox, モデルを使用:Anthropic Claude)
提供された入力質問からのエンティティ抽出用。生成されたテキストからエンティティを抽出し、XMLタグに配置してさらに処理します。
Prompt template for Titan
"""You are an expert entity extractor from provided input question. You are responsible for extracting following entities: {{ list of entities}}
Please follow below instructions while extracting the entity A, and reply in <entityA> </entityA> XML Tags:
{{ entity A extraction instructions}}
Please follow below instructions while extracting the entity B, and reply in <entityB> </entityB> XML Tags:
{{ entity B extraction instructions}}
Below are some examples:
{{ some few shot examples showing model extracting entities from give input }}
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト G1 - プレミアム)
例:
User: You are an expert entity extractor who extracts entities from provided input question.
You are responsible for extracting following entities: name, location
Please follow below instructions while extracting the Name, and reply in <name></name>
XML Tags:
- These entities include a specific name of a person, animal or a thing
- Please extract only specific name name entities mentioned in the input query
- DO NOT extract the general mention of name by terms of "name", "boy", "girl",
"animal name", etc.
Please follow below instructions while extracting the location, and reply
in <location></location> XML Tags:
- These entities include a specific location of a place, city, country or a town
- Please extract only specific name location entities mentioned in the input query
- DO NOT extract the general mention of location by terms of "location", "city", "country",
"town", etc.
If no name or location is found, please return the same input string as is.
Below are some examples:
input: How was Sarah's birthday party in Seattle, WA?
output: How was <name>Sarah's</name> birthday party
in <location>Seattle, WA</location>?
input: Why did Joe's father go to the city?
output: Why did <name>Joe's</name> father go to the city?
input: What is the zipcode of Manhattan, New york city?
output: What is the zipcode of <location>Manhattan,New york city<location>?
input: Who is the mayor of San Francisco?
Bot:
C hain-of-thought 推論
回答がどのように導出されたかについて step-by-step の分析を提供します。モデルが回答をどのように生成したかをファクトチェックして検証します。
Prompt template for Titan
""" {{Question}}
{{ Instructions to Follow }}
Think Step by Step and walk me through your thinking
"""
|
(プロンプトの出典: AWS、使用モデル: Amazon Titan テキスト G1 - プレミアム)
例:
User: If Jeff had 100 dollars, and he gave $20 to Sarah,
and bought lottery tickets with another $20. With the lottery
tickets he bought he won 35 dollars. Jeff then went to buy
his lunch and spend 40 dollars in lunch. Lastly he made a
donation to charity for $20. Stephen met with Jeff and wanted
to lend some money from him for his taxi. How much maximum money
can Jeff give to Stephen, given that he needs to save $10 for
his ride back home?. Please do not answer immediately, think
step by step and show me your thinking.
Bot: