Types of Requests AI Can Handle
Taxonomy of AI tasks: writing, summarizing, answering, coding, brainstorming.
Types of Requests AI Can Handle is a free AI Prompt Engineering lesson on CoddyKit — lesson 2 of 4. You can read the complete lesson below for free — then practise it hands-on in the browser with a built-in code editor and a 24/7 AI tutor. It is part of the AI Prompt Engineering learning path, one of 4 lessons in the course, and your progress syncs across the web and the CoddyKit app.
The AI Task Taxonomy
AI language models are remarkably versatile. They handle a wide range of task types — and knowing which category your task falls into helps you write better prompts.
We can group tasks into: writing, summarizing, Q&A, coding, brainstorming, translation, classification, and data extraction.
Writing Tasks
Writing is one of the most common AI tasks. Examples include:
- Drafting emails, cover letters, blog posts
- Writing short stories, scripts, or creative content
- Composing social media captions
- Editing and rewriting existing drafts
The key is to specify format, tone, length, and audience in your prompt.
import anthropic
client = anthropic.Anthropic(api_key='sk-ant-your-key-here')
response = client.messages.create(
model='claude-opus-4-5',
max_tokens=256,
messages=[{
'role': 'user',
'content': (
'Write a 150-word professional email declining a meeting invitation. '
'Tone: polite and regretful. Suggest rescheduling next week.'
)
}]
)
print(response.content[0].text)Summarization Tasks
Summarization condenses long content into shorter, more digestible form. Common uses:
- TL;DR of long articles or reports
- Meeting notes from a transcript
- Executive summaries of research papers
- Key points extracted from a book chapter
Specify the target length and the level of detail you need.
import openai
client = openai.OpenAI(api_key='sk-your-key-here')
long_text = (
'Artificial intelligence has transformed industries from healthcare '
'to finance over the past decade. Machine learning models now diagnose '
'diseases, detect fraud, and power recommendation engines. However, '
'concerns about bias, privacy, and job displacement remain significant...'
)
response = client.chat.completions.create(
model='gpt-4o',
messages=[{
'role': 'user',
'content': f'Summarize the following in exactly 2 sentences:\n\n{long_text}'
}]
)
print(response.choices[0].message.content)Question and Answer Tasks
Q&A tasks leverage the model's broad knowledge base. Types include:
- Factual questions ('What is the Krebs cycle?')
- Explanatory questions ('How does HTTPS work?')
- Comparative questions ('What is the difference between RAM and storage?')
- Document Q&A — ask questions about a pasted document
For document Q&A, always include the source material in your prompt.
import anthropic
client = anthropic.Anthropic(api_key='sk-ant-your-key-here')
document = 'Our refund policy allows returns within 30 days with receipt...'
response = client.messages.create(
model='claude-opus-4-5',
max_tokens=256,
system='Answer only based on the document provided. If unsure, say so.',
messages=[{
'role': 'user',
'content': f'Document:\n{document}\n\nQuestion: How many days do I have to return an item?'
}]
)
print(response.content[0].text)Coding Tasks
Coding tasks are where AI assistants really shine. Common requests:
- Generate code from a description ('Write a Python function that...')
- Explain what existing code does
- Debug or fix broken code
- Convert code from one language to another
- Write unit tests for a given function
import openai
client = openai.OpenAI(api_key='sk-your-key-here')
response = client.chat.completions.create(
model='gpt-4o',
messages=[
{
'role': 'system',
'content': 'You are a Python expert. Include type hints and a brief docstring.'
},
{
'role': 'user',
'content': (
'Write a function that takes a list of integers and returns '
'the second largest unique value, or None if it does not exist.'
)
}
]
)
print(response.choices[0].message.content)Brainstorming Tasks
Brainstorming uses the AI to generate a large quantity of ideas quickly. Use it for:
- Product name generation
- Blog post topic lists
- Feature ideas for an app
- Marketing campaign angles
- Problem-solving alternatives
Ask for a specific number of ideas and tell the model to prioritize variety over repetition.
import anthropic
client = anthropic.Anthropic(api_key='sk-ant-your-key-here')
response = client.messages.create(
model='claude-opus-4-5',
max_tokens=512,
messages=[{
'role': 'user',
'content': (
'Generate 10 unique app name ideas for a habit-tracking app targeting busy professionals. '
'Each name should be one or two words. Prioritize variety — avoid similar-sounding names. '
'After each name, add a 5-word tagline.'
)
}]
)
print(response.content[0].text)Translation Tasks
Translation goes beyond word-for-word conversion. AI models handle:
- Language translation (English → Spanish, French → Japanese)
- Register translation (technical jargon → plain language)
- Tone translation (formal → casual)
- Format translation (paragraph → bullet points)
Specify if you want a literal translation or a natural, idiomatic one.
import openai
client = openai.OpenAI(api_key='sk-your-key-here')
text_en = 'Please ensure the deliverables are submitted prior to the agreed deadline.'
response = client.chat.completions.create(
model='gpt-4o',
messages=[{
'role': 'user',
'content': (
f'Translate the following into natural, idiomatic Spanish '
f'suitable for a casual work chat message:\n\n{text_en}'
)
}]
)
print(response.choices[0].message.content)Classification Tasks
Classification assigns input into predefined categories. Examples:
- Sentiment analysis (positive / negative / neutral)
- Topic categorization (sports / politics / tech)
- Intent detection (complaint / inquiry / compliment)
- Spam vs. not-spam
Always provide the list of valid categories in your prompt so the model knows what to choose from.
import anthropic
client = anthropic.Anthropic(api_key='sk-ant-your-key-here')
reviews = [
'The product broke after one day. Terrible quality!',
'Shipping was fast and the item is exactly as described.',
'It is okay, nothing special but does the job.'
]
for review in reviews:
response = client.messages.create(
model='claude-opus-4-5',
max_tokens=16,
messages=[{
'role': 'user',
'content': (
f'Classify this review as exactly one of: POSITIVE, NEGATIVE, NEUTRAL.\n'
f'Reply with only the label.\n\nReview: {review}'
)
}]
)
label = response.content[0].text.strip()
print(f'{label}: {review[:40]}...')Data Extraction Tasks
Data extraction pulls structured information out of unstructured text. Common uses:
- Extract names, dates, and amounts from invoices
- Pull key facts from news articles
- Parse contact information from emails
- Extract product specs from descriptions
Ask for JSON output to make it easy to use the extracted data programmatically.
import openai
import json
client = openai.OpenAI(api_key='sk-your-key-here')
email_text = (
'Hi, I am Sarah Johnson from Acme Corp. '
'Please send the invoice for $4,250 to billing@acmecorp.com by June 15th.'
)
response = client.chat.completions.create(
model='gpt-4o',
messages=[{
'role': 'user',
'content': (
'Extract the following fields from the email below and output valid JSON:\n'
'name, company, email, amount, deadline\n\nEmail:\n' + email_text
)
}]
)
raw = response.choices[0].message.content
data = json.loads(raw)
print(data)Combining Task Types
Real-world prompts often combine multiple task types in a single request. For example:
- Extract key claims from an article, then classify each as fact or opinion
- Summarize a document, then translate the summary to French
- Brainstorm ideas, then write a short pitch for the best one
Chaining task types in a single prompt is powerful — just be explicit about each step.
import anthropic
client = anthropic.Anthropic(api_key='sk-ant-your-key-here')
response = client.messages.create(
model='claude-opus-4-5',
max_tokens=512,
messages=[{
'role': 'user',
'content': (
'Do the following in order:\n'
'1. Brainstorm 5 blog post titles about remote work productivity.\n'
'2. Pick the most compelling title.\n'
'3. Write a 3-sentence intro paragraph for that post.\n'
'Format your output with clear numbered sections.'
)
}]
)
print(response.content[0].text)Choosing the Right Task Frame
The same underlying request can be framed in different task types — and the framing changes the output significantly.
Example goal: understand a company's pricing page.
- Q&A frame: 'What are the pricing tiers?'
- Summarization frame: 'Summarize the pricing page in 3 bullet points.'
- Extraction frame: 'Extract plan names and prices as JSON.'
- Comparison frame: 'Create a table comparing all plans.'
Pick the frame that matches how you will use the output.
import openai
client = openai.OpenAI(api_key='sk-your-key-here')
pricing_text = (
'Starter: $9/month - 1 user, 5GB storage. '
'Pro: $29/month - 10 users, 50GB storage. '
'Enterprise: custom pricing - unlimited users.'
)
# Extraction frame
response = client.chat.completions.create(
model='gpt-4o',
messages=[{
'role': 'user',
'content': (
'Extract plan names and monthly prices as a JSON array. '
'Use null for custom pricing.\n\n' + pricing_text
)
}]
)
print(response.choices[0].message.content)Knowledge Check
You have learned the main categories of AI task types. Let's see if you can identify the right one.
A developer pastes a 500-word customer support email into a prompt and asks the AI: 'Pull out the customer name, order number, and issue type — output as JSON.'
Which task type is this?
Task Taxonomy Recap
You can now identify and frame any AI request as one of the core task types:
- Writing — generating original text content
- Summarization — condensing long content
- Q&A — answering questions from knowledge or documents
- Coding — generating, explaining, or debugging code
- Brainstorming — generating many diverse ideas
- Translation — converting between languages or registers
- Classification — assigning input to predefined categories
- Data Extraction — pulling structured data from unstructured text
Name the task type first — then write the prompt around it.
Frequently asked questions
Is the “Types of Requests AI Can Handle” lesson free?
Yes — the full text of “Types of Requests AI Can Handle” is free to read here on the web, and the AI Prompt Engineering course includes 4 lessons in total. To practise it interactively (a built-in code editor and a 24/7 AI tutor) and unlock the rest of the AI Prompt Engineering course, upgrade to CoddyKit PRO.
What will I learn in “Types of Requests AI Can Handle”?
Taxonomy of AI tasks: writing, summarizing, answering, coding, brainstorming. You practise AI Prompt Engineering with hands-on code you run directly in the browser, and a 24/7 AI tutor answers your questions as you work through the lesson.
Do I need any experience to start AI Prompt Engineering?
No prior experience is required. AI Prompt Engineering on CoddyKit is structured for beginners through advanced learners; this is — lesson 2 of 4, so you can start here or from the beginning and move at your own pace.
How long does the “Types of Requests AI Can Handle” lesson take?
Most CoddyKit lessons take about 5–10 minutes. Each one is bite-sized and interactive, so you make steady progress and pick up exactly where you left off across the web and the app.
Can I write and run code in this AI Prompt Engineering lesson?
Yes. Every AI Prompt Engineering lesson includes a built-in code editor, so you write and run real code right in your browser and get instant AI feedback — no local setup required.
All lessons in this course
- Understanding the Chat Interface
- Types of Requests AI Can Handle
- How AI Generates Responses
- What AI Cannot Do