We let AI agents run 23 vacation rental properties. Here is what we never let them do

Description and use

AI agents manage 23 vacation rentals, handling pricing, messaging, and booking expiry tasks under strict code‑based guardrails instead of prompt instructions. This reduces manual effort, builds trust, and keeps critical decisions under human control.

Problem

Managing 23 vacation rental properties required repetitive, time‑consuming tasks such as answering parking questions and setting nightly prices, which ate into the operator’s evenings.

Outcome

The operator now manages 23 properties with AI agents that handle repetitive tasks while preserving human oversight for critical decisions, leading to reduced workload and consistent application of business rules.

Workflow

• 1. Deploy agents in Suggest mode for each task (pricing, messaging, expiry).
• 2. Agents generate proposals and return them to the operator.
• 3. Operator reviews, edits if necessary, and approves or rejects the proposal.
• 4. Once approved, the agent can be switched to Auto mode for that task.
• 5. Code enforces constraints (price floor, no irreversible actions, no money spent) after the model returns.
• 6. Agents act only when no human has intervened (silence) and in the safe direction (e.g., decline booking if no response within 15 minutes).

Evidence

The guardrail goes in code, not in the prompt

Source

Ship every agent switched off, and make the user turn it up

Source

When it fails, work out which direction is safe

Source