Skills and agents · Practical guide
Build a human approval queue for AI-assisted work
- Tools
- Multi-tool
- Audience
- People getting started with AI
- Topic
- Skills and agents

You’ll finish with: a visible queue that keeps a human accountable for execution.
Drafting and approving are different jobs. Put a visible gap between them, so a helpful assistant cannot turn “looks promising” into a sent message. An approval queue can start as a plain table.
Set up
Allow 25 minutes. Use a spreadsheet or document and a chat tool. No live sending integration is needed for the first version.
Try this example
FICTIONAL PRACTICE MATERIAL
Queue items: draft venue query, owner Jo; proposed AUD 50 credit, approver not assigned; draft training reminder, owner Lee. Status choices: Draft, Needs review, Approved, Sent.Do the task
- Create an item ID, draft text, reviewer, status and decision note for each item.
- Ask AI to prepare drafts and put all three into Needs review, without executing them.
- Check that only a real reviewer can record approval and that approved content is not silently changed afterwards.
Your reusable prompt
Build an approval queue from these items. Leave the credit approver Unknown. Draft messages only. Include the exact version reviewed and a field for the human decision; do not mark anything Approved.
PRACTICE INPUT
Queue items: draft venue query, owner Jo; proposed AUD 50 credit, approver not assigned; draft training reminder, owner Lee. Status choices: Draft, Needs review, Approved, Sent.
Refine your result
Add a rule that changing approved wording returns the item to Needs review. Separate approval from the later send action.Check the result
No row should be Sent. The unassigned credit cannot move forward until the proper authority is identified. A status word in a spreadsheet does not itself enforce an API permission.
Save and reuse
Save approval-queue.csv and test one approve/revise cycle manually before connecting a sender.
Sources and notes
- Tool permission controls in Claude Code Checked 2026-10-05
- The practice input and teaching prompt are original 5HO material. Examples are fictional; they are not screenshots or claims of a completed real-world task.
- Official documentation supports the relevant product concepts. Setup availability depends on your account; where a guide offers a fallback, it does not prove the connected capability worked.