Skip to main content
Back to Prompt Library
implementation

Construct Claude Agents SDK Extended Thinking Agent

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

Linked challenge: Vaccine Safety Literature Synthesis Agent with Claude Agents SDK

Format
Code-aware
Lines
9
Sections
3
Linked challenge
Vaccine Safety Literature Synthesis Agent with Claude Agents SDK

Prompt source

Original prompt text with formatting preserved for inspection.

9 lines
3 sections
No variables
0 checklist items
import anthropic

# Initialize Claude client with tool use and extended thinking for deep literature synthesis
client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-3-7-sonnet-20250219",
    max_tokens=4000,
    thinking={"type": "enabled", "budget_tokens": 2000},
    messages=[{"role": "user", "content": "Analyze epidemiological evidence..."}]
)

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.