Back to Prompt Library
planning
Designing the Multi-Agent Framework
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Accelerating Obesity Drug Lead Optimization
Format
Text-first
Lines
1
Sections
1
Linked challenge
Accelerating Obesity Drug Lead Optimization
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
As a principal AI architect, design a CAMEL-based multi-agent system for lead compound optimization targeting obesity. Define at least three distinct agent roles (e.g., 'Chemist Agent', 'Biologist Agent', 'ADMET Specialist Agent'), their responsibilities, and how they will communicate to iteratively propose, evaluate, and refine lead structures. How will you use a tool like StarCoder 2 to assist agents in generating relevant code snippets or chemical reactions?
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.