Design an Orchestrator + Worker Multi-Agent System
Plan a supervisor agent that breaks a task into subtasks and delegates to specialized worker agents, then merges their results.
Get a clear topology, message contract, and merge strategy for a multi-agent system instead of an unpredictable swarm.
At a glance
Access
Free prompt
Open to copy — no account or payment needed.
Prompt objective
Get a clear topology, message contract, and merge strategy for a multi-agent system instead of an unpredictable swarm.
Real use case
A team wants to automate competitive research: one agent gathers sources, another extracts facts, a third writes the brief. They need a coordinator that keeps them in sync and avoids duplicated work.
Customize these fields first
Replace the placeholders with your own context before you run the prompt. That usually improves the first output more than adding more instructions later.
Prompt
You are a multi-agent systems architect. Design an orchestrator-and-workers system for the task below. Overall task: [TASK] Desired final output: [DELIVERABLE] Constraints: [LATENCY, COST, ACCURACY] Produce: 1. Agent roster: the orchestrator plus each worker agent, with a one-line responsibility for each. Keep the roster as small as possible. 2. Topology diagram described in text (who calls whom, what flows in each direction). 3. Message contract: the JSON shape passed between orchestrator and workers (task id, instructions, inputs, expected output schema). 4. Delegation logic: how the orchestrator decides which worker handles what, and how it parallelizes independent subtasks. 5. Merge strategy: how partial results are combined, conflicts resolved, and gaps detected. 6. Failure handling: what happens when a worker fails, stalls, or returns low-confidence output. 7. A worked example trace for one realistic input. Prefer the simplest design that meets the goal. Flag where a single agent would actually be better than multiple.
Open directly in an AI — the text is pre-filled:
How to use this prompt
- 1Replace the key placeholders first: TASK, DELIVERABLE, LATENCY, COST, ACCURACY.
- 2Replace any bracketed placeholders like [this] with your own context.
- 3Add extra background information when you want more tailored results.
- 4Combine multiple prompts in one conversation when you need a richer output.
- 5Save your best-performing prompts so they are easy to reuse later.
Next best step
Open the guide first, then branch only if you still need more.
A guide for technical builders choosing between prompts, coding workflows, and agent-based implementation.
If this prompt is close but not quite right, generate variants next. If the job is recurring, move into the course library after the guide.
Related prompts
View allRun an Adversarial Reviewer Agent Over Another Agent's Output
Set up a critic agent that stress-tests a generator agent's work against explicit criteria before anything ships.
Best for
Catch errors, hallucinations, and missed requirements automatically by pairing a maker agent with a skeptical reviewer agent.
Define Handoff Contracts Between Specialized Agents
Write the exact input/output schemas and handoff rules so agents pass work cleanly without losing context.
Best for
Eliminate the most common multi-agent failure — broken handoffs — by making every transfer a typed, validated contract.
Explore other prompt categories
Move sideways into adjacent libraries when the current category is not the full answer.
Every prompt here is free. The course teaches the thinking behind them.
Copy as many prompts as you like. When you want to move from single prompts to a repeatable AI workflow, Learn AI in 30 Days walks through it, one day at a time.
Buy the course once ($15/$20 by length), or go all-access for $10/mo with a verifiable certificate.