Agents

Multi-Agent Task Decomposer

Split a job across agents without overlap or gaps.

The Prompt

I want a multi-agent system that [goal].
Design it:
1. The 2-4 agents, each with ONE job and one sentence of scope
2. The contract between them: exactly what artifact each produces and consumes
3. Where a shared state beats message-passing, and vice versa
4. The most likely coordination failure and how the design prevents it

 Fill in before using

[goal]

How to use it

→ Paste the prompt into your model of choice — it works with any frontier model.
→ Replace every bracketed placeholder with your specifics. Concrete inputs beat vague ones every time.
→ If the model asks a clarifying question, answer it — these prompts are designed to invite that.
→ Iterate on the output, not the prompt. The structure is already tuned.

multi-agentarchitecture

More Agents prompts

Agent System Prompt Skeleton

A battle-tested structure for tool-using agents.

Tool-Use Critic

Audit an agent trace for wasted calls and loops.

Human Handoff Policy

When the agent should stop and escalate.