Back to Prompt Library
planning

Design Agent Workflow

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

Linked challenge: Multi-Agent Ad Fraud Detection

Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Agent Ad Fraud Detection

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Design a LangGraph workflow for ad fraud detection. Define roles for at least three agents (e.g., 'Ad Ingestor', 'Creative Analyzer', 'Policy Analyst', 'Fraud Investigator'). Outline their responsibilities, the states they manage, and the conditional logic for transitions. Describe how A2A Protocol will facilitate their communication and how MCP will enable tool access to a mock ad platform API and a policy database.

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.