Back to Prompt Library
implementation
Claude Agents SDK VASP Initialization
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Claude Agents SDK Virtual Asset Compliance Auditor
Format
Code-aware
Lines
14
Sections
3
Linked challenge
Claude Agents SDK Virtual Asset Compliance Auditor
Prompt source
Original prompt text with formatting preserved for inspection.
14 lines
3 sections
No variables
0 checklist items
import anthropic
client = anthropic.Anthropic()
# Configure message request with extended thinking budget
response = client.messages.create(
model='claude-3-7-sonnet-20250219',
max_tokens=4000,
thinking={'type': 'enabled', 'budget_tokens': 1024},
tools=[{
'name': 'check_vasp_registry',
'description': 'Looks up VASP licensing status in MAS database',
'input_schema': {'type': 'object', 'properties': {'vasp_id': {'type': 'string'}}}
}],
messages=[{'role': 'user', 'content': 'Audit transfer VA-8819 for Travel Rule compliance.'}]
)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.