cd /news/ai-agents/which-of-your-agent-s-actions-can-t-… · home › topics › ai-agents › article
[ARTICLE · art-171963] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Which of Your Agent's Actions Can't Be Undone?

A practitioner who advises businesses on deploying AI agents safely recommends auditing every action an agent can take before it goes live, then flagging irreversible ones—refunds, cancellations, outbound emails, payments—for mandatory human sign-off. The approach treats a tool as an action with a shorter name and asks, for each capability, whether a mistake can be fully and quickly reversed with little harm to the customer or business. The author advises erring toward the sign-off list, since permissions can be loosened later but a sent message or payment cannot easily be undone.

recommendation

Before launch, list each action and tool the agent can invoke and gate irreversible ones—refunds, cancellations, emails, payments—behind human approval, erring toward sign-off when unsure.

more in playbook: Securing agents and AI tools
by read2 min views1 publishedNov 18, 2026

An AI agent that only drafts a reply is one kind of risk. An agent that can issue a refund, cancel an order, send an email or move money is another. The second kind can create a result you cannot take back, or cannot take back easily, before a person has even seen it.

The practical move is simple, and it should happen before the agent goes live: list every action it can take, mark the ones you cannot undo and require a human sign-off for those.

People often describe an agent by its job title: "it handles support," "it books appointments," "it follows up with leads." That is not a list of actions.

Sit down with whoever configured the agent and write down each thing it is allowed to do. Be concrete. Say your support agent can answer a question, look up an order, start a return, issue a refund, cancel a subscription, change an address, send an email or create a credit. A scheduling agent might book, cancel, reschedule or message a customer. A sales agent might quote a price, apply a discount, send a proposal or update a record.

If the agent can use tools, include those too. A tool is an action with a shorter name. Then, for each action, ask one question: if this goes wrong, can we fully reverse it, quickly, and with little harm to the customer or the business?

Some actions are easy to reverse. A wrong draft that a person still has to send is not live yet. A note added to an internal record can be edited.

Other actions travel farther:

You do not need a perfect legal definition. You need an honest line: if we would be uncomfortable seeing this go out with no person in the loop, it belongs on the "sign-off required" list.

When in doubt, put it on that list. You can always loosen a rule later. You cannot unsend a message or reverse a payment with the same ease.

Once you have the list, change the agent's permissions to match it.

The point is not to slow every answer. Most questions do not need a sign-off. The point is to keep a person in the loop for the few actions that can create a mess.

If you cannot answer the first two questions, you do not yet know what the agent can do in your name. That is the risk. The list comes first; the sign-off comes next. I work with businesses on putting AI agents to work safely, through training, pilots and safety checks. If your agent can already take actions for you, I'd like to hear which ones require a person to sign off, and how you drew that line. Reply and tell me how you handle it.

── more in #ai-agents 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/which-of-your-agent-…] indexed:0 read:2min 2026-11-18 · —