# Make your AI agent stop for approval

> Researched. Small business · Beginner · Operations. Updated 2026-11-02.

Canonical page: https://www.aisetupsthatwork.com/setups/make-your-ai-agent-stop-for-approval-before-it-sends/

## What it does
Make your AI agent stop and show you every email, booking or post as a draft with a one-line summary, and wait for your OK before it goes out.

## Who it's for
Anyone whose AI assistant can send, book or post through connected apps, and who wants a human check on everything that leaves the business.

## Tools
- ChatGPT or Claude with the apps you use connected
- The agent's project or custom instructions

## Steps
1. Find where your agent keeps standing instructions: project instructions, custom instructions or the agent's settings.
2. Paste the approval rule from the prompt below. It turns every outgoing action into a draft plus a short summary of who, what and when.
3. Keep the tool's own approval setting on as a second lock. Anthropic says its Google Workspace connectors ask for approval before sending, replying or forwarding by default.
4. Test it: ask the agent to email yourself a fake quote. It should stop and show the draft, not send.
5. Approve with a clear word, such as SEND, so a vague reply like ok does not count as approval.
6. If it ever sends without asking, disconnect that app, tighten the instruction and test again.

## Copy-paste prompt
Adapt bracketed fields to your situation.
```text
Add this rule to your standing instructions and follow it every time:

Before anything leaves my business (email, message, booking, calendar invite, post, payment, refund):
1. Prepare it as a draft only.
2. Show me: who it goes to, the full text, and when it would go out.
3. Add one line: what could go wrong if this is wrong.
4. Wait. Only proceed when I reply with the word SEND for that item.
5. If I reply with anything else, treat it as an edit or a no.

If you are unsure whether something counts as leaving the business, treat it as if it does.
```

## Guardrails
- What it touches: Chat input you provide (ChatGPT or Claude with the apps you use connected; The agent's project or custom instructions).
- Needs your OK: Send, pay, publish, delete, and CRM updates stay with you unless you explicitly opt in.
- Safety level: Drafts for you
- The instruction lives in one chat, so a new chat forgets it. Put it in project or custom instructions.
- Turning off the tool's own approval setting because the agent asks anyway. Keep both.
- Approving from your phone without reading the recipient line.

## Tips
- One approval word per item stops a single yes from releasing a whole batch.
- Ask for the one-line risk note; it makes bad drafts obvious at a glance.
- Re-test after any change to the agent's apps or model.

## Estimates (labeled, not measured)
- Time saved: About 10 minutes to set up and test.
- Money saved: Not stated in sources.
- Tool cost: Works on free tiers for drafting. Connected-app agents may need a paid plan; prices: Not stated in sources.

## Sources
Summaries use the public sources below, not independent verification.
- Anthropic: https://support.claude.com/en/articles/10166901-use-google-workspace-connectors (Use Google Workspace connectors: Gmail drafting, approval before send, reply or forward by default (read 2026-10-31 through a page fetch tool, not a direct browser open))
- OpenAI: https://help.openai.com/en/articles/11752874-chatgpt-agent (ChatGPT agent: when signed into sites or apps it can access sensitive data like emails, files or account settings and perform actions (read 2026-11-02 from the official help page via search))
- OpenAI: https://help.openai.com/en/articles/10169521-projects-in-chatgpt (Projects in ChatGPT: keep chats, files and instructions together; owners update instructions and add files (read 2026-11-02 from the official help page via search))

## Get the free starter pack
Five beginner copy-paste AI setups, free by email: https://www.aisetupsthatwork.com/starter-pack/?utm_source=ai-agent&utm_medium=markdown&utm_campaign=setup-make-your-ai-agent-stop-for-approval-before-it-sends

Related:
- [Set guardrails before an AI agent gets access](https://www.aisetupsthatwork.com/setups/set-guardrails-before-giving-an-ai-agent-access/index.md)
- [Morning inbox briefing and multi-inbox triage](https://www.aisetupsthatwork.com/setups/inbox-morning-triage/index.md)
- [Give each AI agent its own email](https://www.aisetupsthatwork.com/setups/give-each-ai-agent-its-own-mailbox/index.md)