Back to Prompt Library
planning
Initialize Claude Agents SDK and Pydantic Schema
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Cyber Threat Intelligence Triage Agent using Claude Agents SDK and Pydantic AI
Format
Code-aware
Lines
1
Sections
1
Linked challenge
Cyber Threat Intelligence Triage Agent using Claude Agents SDK and Pydantic AI
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Import Agent from anthropic_agents or claude_agent_sdk and Agent from pydantic_ai. Define a structured output class `ThreatReport` using Pydantic, specifying severity, confidence_score, and mitigation_action.
Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Tune next
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Verify after
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.