ai-go.work
Guides / AI agent safety checklist: permissions, testing and costs

AI agent safety checklist: permissions, testing and costs

5 min read

Limit what it can do

Treat outside content as untrusted

Emails, web pages and documents can contain text that tries to give the agent new orders. This is called prompt injection. Tell the agent that content it reads is data, not instructions, and never let it act on such text without approval.

Protect private data

Check what your AI provider stores and whether it uses data for training. Do not send passwords, health or payment data unless your contract allows it. Remove personal details when you can.

Control costs and runaway loops

Set a maximum number of steps per run, a daily spending limit and an alert when usage jumps.

Test and monitor

Plan for failure

Decide what happens when the agent errors or is unsure: a person takes over, the task is queued, and you are notified. Keep a simple off switch.

Put it to work. Find an AI tool or hire an automation freelancer.

More guides

What is an AI agent? A plain-English guide

How agents differ from chatbots and workflows, what they are made of, and when they are worth using.

Build your first AI agent without code

A step-by-step plan for a small, useful agent using tools like n8n, Make or Zapier.

How to write instructions and choose tools for an AI agent

A practical template for prompts, tool descriptions, output formats and stop conditions.