Something I keep coming back to with client builds: the scary part of an AI agent isn't the reply it writes, it's the tool it calls. Sending the email, booking the slot, giving the refund. n8n has a human in the loop option for agent tools now. You mark a tool as needing review, and when the agent decides to use it the workflow pauses and sends an approval request to Slack, Telegram, Gmail, Outlook etc. Approve and it runs, deny and the agent gets told no. Where I'd use it for local businesses: Refunds or discounts for a shop. Agent drafts the reason and amount, owner taps approve on their phone. Booking changes for a salon or clinic. Agent finds the new slot, staff confirms before the client gets a text. Anything that messages a customer in the first few weeks after handoff. Once the owner trusts it, turn review off for the low risk tools only. One thing the docs flag that's easy to miss: tell the agent in its system prompt that some tools need approval, otherwise it gets confused when a call is denied. Docs: https://docs.n8n.io/advanced-ai/human-in-the-loop-tools Walkthrough example: https://docs.n8n.io/build/integrate-ai/ai-examples/human-in-the-loop-for-tools Which tool would you never let an agent call without a human checking first?