Experiment Design Reviewer
NewReviews an experiment for causal validity, measurement quality, and interpretation risks.
This prompt has no customizable variables — it's ready to use as-is.
Act as a multi-agent orchestration architect.
Objective:
Design a supervisor-worker system only when specialization or parallelism creates real value.
Inputs:
- worker capabilities: {{WORKER_CAPABILITIES}}
- task types: {{TASK_TYPES}}
- shared data: {{SHARED_DATA}}
- latency limits: {{LATENCY_LIMITS}}
- human escalation rules: {{HUMAN_ESCALATION_RULES}}
Process:
1. Determine whether multi-agent architecture is justified.
2. Define each worker’s narrow responsibility and input/output contract.
3. Design routing and delegation rules for the supervisor.
4. Specify context passing, state ownership, concurrency, and conflict resolution.
5. Define termination, retry, and escalation behavior.
Required output:
- Supervisor policy
- Worker contracts
- Routing matrix
- State model
- Handoff protocol
- Failure strategy
- Evaluation scenarios
Guardrails:
- Do not let agents delegate indefinitely.
- Avoid duplicated responsibilities across workers.
- Keep the supervisor from performing specialist work unless explicitly required.
When information is missing, state the assumption explicitly and identify what evidence would change the recommendation. Keep the response practical, specific, and implementation-oriented."Run with AI" sends your customized inputs to this site's configured AI model to generate a live sample here — nothing is saved. To keep your content on the provider's own site instead, use Copy or Open in ChatGPT.
Did this prompt give you a useful result?
Use this prompt to define delegation logic, shared context, handoffs, retries, escalation, and stopping conditions for multi-agent systems.
Reviews an experiment for causal validity, measurement quality, and interpretation risks.
Synthesizes interviews, surveys, and notes into actionable user insights.
Reviews whether citations actually support the claims they are attached to.
Recommends a research design that fits the question, constraints, and available evidence.