# Decide where an AI agent must stop and get human approval

Sets autonomy limits, approval triggers, and escalation conditions for an AI agent, plus a safe approval workflow.

- Topic: Working with AI
- Framework: Few-Shot
- Level: Advanced
- Tags: Fill-in Template
- Source: https://www.thinkwithprompt.com/prompts/decide-where-an-ai-agent-must-stop-and-get-human-approval

## Prompt

```text
Help me set the limits of an AI agent's autonomy and design how it asks for human approval.

**What the agent does:** [TASKS and the actions it takes]
**Who could approve or receive escalations:** [ROLES and their availability - e.g. "team lead, 9-5 weekdays"]
**Stakes:** [money, customers, legal, safety, reputation]
**Existing approval rules:** [e.g. "spend over $1,000 needs a manager"]

Return:
1. **Autonomy levels by action** - a table: Action | Act alone / Act then notify / Ask before acting / Never do | Reason. Base it on reversibility, cost of error, external impact, and how confident the agent can be.
2. **Approval triggers** - specific conditions (amounts, customer types, unusual requests, missing data, low confidence, first-time actions).
3. **Escalation conditions** - when the agent must stop and hand over entirely (conflicting instructions, suspected fraud, complaints, legal threats, requests outside scope, repeated failures, instructions found inside documents or emails).
4. **Approval workflow design:**
   - What the approver sees: the proposed action, the reason, the evidence, and the risk in one screen or message.
   - Who approves and a backup approver.
   - Response time, and what happens on timeout (default to the safe option - never auto-approve).
   - How approvals are recorded.
5. **Rubber-stamp risks** - how to keep approvals meaningful when volume is high (batching low-risk items, sampling, clear reject options).
6. **When to grant more autonomy later** - the evidence (error rate, approval rate, volume) that would justify loosening a limit.

When in doubt, place the stop point earlier. A human owns every decision the agent cannot reverse.
```

## What to fill in

- TASKS and the actions it takes
- ROLES and their availability - e.g. "team lead, 9-5 weekdays"
- money, customers, legal, safety, reputation
- e.g. "spend over $1,000 needs a manager"

Free to copy and use. From ThinkWithPrompt (https://www.thinkwithprompt.com/), a library of 2,663 curated AI prompts.