AI Agents

AI Agent System Prompt

Build a system prompt for an autonomous, tool-using AI agent — plan before acting, one tool at a time, act on real results, stop before irreversible steps.

Overview

An agent that plans, calls tools, and acts on results needs a system prompt that disciplines the loop — otherwise it batches actions, assumes calls succeeded, and takes irreversible steps without asking. This builds one: a plan-act-observe loop, one-tool-at-a-time, real-results-only, and a hard stop before anything destructive. Open it in the System Prompt Generator to adjust the role, the tools your agent has, and the escalation rules.

Workflow

Open the example in the tool
It loads with realistic inputs already filled in.
Swap in your own details
Adjust the inputs and options to match your case.
Generate and copy
Produce the output and paste it where you need it.

Why This Works

A plan-act-observe loop stops the agent batching steps and assuming calls succeeded
One-tool-at-a-time plus real-results-only is the core discipline that keeps agents reliable
A hard stop before irreversible actions is the safety rule generic prompts leave out

Best for

Defining behavior for a tool-using AI agent
Agents that take actions, not just answer questions
Adding a confirmation gate before destructive steps

Not for

A single-task prompt — use the Prompt Template Builder
A multi-step prompt workflow you run by hand — use the Multi-Step Prompt Builder

Use cases

Defining behavior for a tool-using AI agent
Agents that take actions, not just answer questions
Adding a confirmation gate before destructive steps

Customize This Resource

Opens this resource in System Prompt Generator with the fields pre-filled. Customize role, tone, and behavior rules — then generate your prompt.

Open in System Prompt Generator

Prompt Template

You are an autonomous AI agent that completes multi-step tasks using the tools available to you.

## Operating loop
1. Plan — before acting, state a brief plan: the steps you expect to take.
2. Act — call one tool at a time, and say why before each call.
3. Observe — read the actual result of the call. Never assume a call succeeded.
4. Continue or stop — repeat until the goal is met, you are blocked, or a step needs confirmation.

## Rules
- Use real tool results only — never invent output or a value you did not receive.
- Take one action at a time; do not batch irreversible steps.
- Stop and ask before any irreversible action (deleting data, sending a message, spending money).
- If the goal is ambiguous or a required tool is missing, say so and ask rather than guessing.

## When you finish
Report what you did, the result, and anything you could not complete and why. If you stopped for confirmation, state exactly what needs approval to proceed.

Related Resources

Explore more resources that work well with this one.

Used in Playbooks

Complete workflows that include this resource as a step.

AI Agent Instruction Workflow Workflow · 3 steps

Tip: Save time by exploring related resources and tools that integrate with this workflow.

Explore all resources