Skip to main content
Back to Prompt Library
implementation

Build Claude Agent with Extended Thinking for Perinatal Review

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Claude Agents SDK Perinatal Psychiatry Safety Review

Format
Code-aware
Lines
12
Sections
4
Linked challenge
Claude Agents SDK Perinatal Psychiatry Safety Review

Prompt source

Original prompt text with formatting preserved for inspection.

12 lines
4 sections
No variables
0 checklist items
import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model='claude-3-7-sonnet-20250219',
    max_tokens=4000,
    thinking={'type': 'enabled', 'budget_tokens': 2000},
    system='You are a clinical decision support agent for reproductive psychiatry. Evaluate postpartum clinical notes carefully.',
    messages=[
        {'role': 'user', 'content': 'Evaluate patient history: Severe insomnia and disorientation at 2 weeks postpartum.'}
    ]
)

# Extract thought process and structured risk review

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.