Extract the key dates and events from the following text:

<text>
[paste text]
</text>

Output format: JSON with keys "date", "event", "description"

Can you tell me what dates are in this text?

<examples>
<example>
<input>
The conference is scheduled for March 15, 2025 in San Francisco.
</input>
<output>
{
  "date": "2025-03-15",
  "event": "conference",
  "location": "San Francisco"
}
</output>
</example>

<example>
<input>
Our next board meeting is on June 22nd.
</input>
<output>
{
  "date": "2025-06-22",
  "event": "board meeting"
}
</output>
</examples>

<input>
The product launches on September 1st in New York.
</input>

<output>

I need to decide between these two job offers. Let me think through this step by step.

<job_offer_a>
[details]
</job_offer_a>

<job_offer_b>
[details]
</job_offer_b>

Please analyze both offers, show your reasoning, and provide a recommendation.

<thinking>
First, let me analyze the compensation...
Then consider the growth potential...
The work-life balance factors are...
The company stability differs by...
</thinking>

<answer>
[conclusion]
</answer>

What's the most efficient route to visit all these cities?

Let's think step by step.

<task>
Extract relevant quotes from this document related to [topic].
</task>

<document>
[paste document]
</document>

<output_format>
<quotes>
<quote>[relevant quote 1]</quote>
<quote>[relevant quote 2]</quote>
</quotes>
</output_format>

<task>
Summarize the extracted quotes and synthesize key insights.
</task>

<quotes>
[from previous response]
</quotes>

<output_format>
<summary>
[executive summary]
</summary>

<key_insights>
<insight>[insight 1]</insight>
<insight>[insight 2]</insight>
</key_insights>
</output_format>

<question>
[research question]
</question>

<thought_1>
[what needs to be done first]
</thought_1>

<action_1>
[tool use or information gathering]
</action_1>

<observation_1>
[result from action]
</observation_1>

<thought_2>
[next step based on observation]
</thought_2>

<final_answer>
[conclusion]
</final_answer>

<problem>
[complex problem]
</problem>

<thought_paths>
<path_1>
<assumption>[approach 1]</assumption>
<reasoning>[step-by-step]</reasoning>
<conclusion>[result]</conclusion>
</path_1>

<path_2>
<assumption>[approach 2]</assumption>
<reasoning>[step-by-step]</reasoning>
<conclusion>[result]</conclusion>
</path_2>

<path_3>
<assumption>[approach 3]</assumption>
<reasoning>[step-by-step]</reasoning>
<conclusion>[result]</conclusion>
</path_3>
</thought_paths>

<synthesis>
[best path and why]
</synthesis>

<context>
[background information]
</context>

<task>
[what needs to be done]
</task>

<examples>
[example inputs and outputs]
</examples>

<input>
[the actual input to process]
</input>

<output_format>
[expected format]
</output_format>

[TASK_CONTEXT]
Setting the stage and overall context

[TONE_CONTEXT]
How Claude should approach the task

[INPUT_DATA]
The actual data to work with

[EXAMPLES]
Few-shot examples

[TASK_DESCRIPTION]
Specific task details

[IMMEDIATE_TASK]
The immediate action to take

[OUTPUT_FORMATTING]
Expected output structure

response = client.messages.create(
    model="claude-sonnet-4-5-20250929",
    max_tokens=4096,
    thinking={
        "type": "enabled",
        "budget_tokens": 8192
    },
    messages=[{
        "role": "user",
        "content": "Analyze this complex problem..."
    }]
)

<task>
[complex reasoning task]
</task>

<thinking>
[Claude will show its reasoning here]
</thinking>

<answer>
[final answer]
</answer>

System: You are a technical writer specializing in API documentation. Your responses are always:
- Clear and concise
- Technically accurate
- Formatted with Markdown
- Focused on developer needs

User: [your actual query]

<task>
Analyze this document and extract key findings.
</task>

<document>
[paste document]
</document>

<response>
<summary>
[Claude continues from here]

<cached_content cache_control="{\"type\":\"ephemeral\"}">
[large context that doesn't change]
</cached_content>

<task>
[specific task that varies]
</task>

<task>
Analyze this data and create a visualization.
</task>

<tools>
- Web search for market data
- Code execution for analysis
- File write for chart output
</tools>

Claude will execute these in parallel when possible.

<task>
When working on ongoing projects, create a memory file to track:
- Key decisions and rationale
- Project context and constraints
- Preferences and patterns
</task>

Claude will automatically update and reference memory files when given local file access.

undefined

undefined

<task>
[specific analysis task]
</task>

<document>
[paste document]
</document>

<output_format>
[expected structure]
</output_format>

<task>
Write a function that [description]
</task>

<requirements>
[specific requirements]
</requirements>

<examples>
<example>
<input>[input example]</input>
<output>[expected output]</output>
</example>
</examples>

<output_format>
[code in specified language]
</output_format>

<task>
Extract [specific fields] from the following text
</task>

<input_text>
[paste text]
</input_text>

<output_format>
JSON with keys: [list keys]
</output_format>

undefined

undefined

undefined

Most prompting techniques remain unchanged—XML tags, system prompts, and structured outputs work identically.