Back to Prompt Library
planning

Initialize Agent System

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

Linked challenge: Multi-Agent Code Review & Refactoring

Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Agent Code Review & Refactoring

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Design the core architecture for your multi-agent system using the OpenAI Agents SDK. Define at least two specialized agents: a 'Code Reviewer Agent' focused on identifying issues and a 'Refactor Suggestor Agent' responsible for generating improved code. Both agents should leverage the o4-mini model for their reasoning capabilities. Provide the Python code for initializing these agents, their initial instructions, and any dummy tool definitions required to simulate their functions.

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.