563
Prompt

Multi-Agent Role Definition Prompt

Generates crisp role prompts and handoff contracts for a team of agents.

1 min readupdated 2026-08-01

/ quick answer

Use when splitting one overloaded agent into a small team. Generates crisp role prompts and handoff contracts for a team of agents.

Generates crisp role prompts and handoff contracts for a team of agents. Use when splitting one overloaded agent into a small team. Copy the prompt below, swap the bracketed variables for your own context, and run it in any capable model. This prompt node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Context
Use when splitting one overloaded agent into a small team.
Prompt
You are designing a multi-agent system. Given the goal below, return:

1. ROLES — for each agent: name, single-sentence mandate, allowed tools, forbidden actions.
2. SYSTEM PROMPT — a ready-to-use prompt for each role (max 150 words each).
3. HANDOFF CONTRACTS — the exact JSON payload each agent passes to the next.
4. SUPERVISOR LOGIC — routing rules, retry limits, stop conditions.
5. OVERLAP CHECK — call out any two roles that could be merged, and recommend merging them if the split adds no value.

Goal: {{GOAL}}
Constraints: {{CONSTRAINTS}}
Example Output
1. ROLES — Researcher: gathers and verifies claims. Tools: web_search, fetch_page. Forbidden: writing prose...
Related Workflow
Related Tool Stacks
/ frequently asked

What does the Multi-Agent Role Definition Prompt prompt do?

Use when splitting one overloaded agent into a small team.

Which AI models work with this prompt?

It is model-agnostic: it works with any capable general model. Replace the bracketed variables with your own context before running it.

What output should I expect?

1. ROLES — Researcher: gathers and verifies claims. Tools: web_search, fetch_page. Forbidden: writing prose...

/ continue exploring

Related concepts

The vocabulary this page depends on.

  • Multi-Agent System

    A multi-agent system splits a job across several specialised AI agents that coordinate through a shared plan, message bus or orchestrator.

  • Agent Handoff

    Agent handoff is the controlled transfer of a task — with its context — from one agent to another agent or to a human.

  • AI Orchestration

    Coordinating multiple AI models, tools and steps into a single reliable workflow.

  • Agent Architecture

    Agent architecture is the structural blueprint of an AI agent: the model, the planning loop, the tools, the memory layer and the guardrails that decide how it acts.

all dictionary

Related workflows

Turn this into a repeatable process.

all workflows

Related tool stacks

The tools that run it in production.

all tool stacks

Related prompts

Reusable prompts for this job.

all prompts

Related use cases

How people apply it, and what came out.

all use cases

Comparisons & alternatives

Pick between the options.

  • Single Agent vs Multi-Agent System

    One well-equipped agent beats a crowd for most jobs; multi-agent wins on genuinely separable, parallel work.

  • AI Agent vs Trading Bot

    A trading bot executes fixed rules deterministically; an AI agent interprets context and decides which steps to take — powerful for research, risky for execution.

all comparisons