Skip to content

Responsible automation guide

Where human approval belongs in travel AI

The important question is not simply whether an AI agent can perform an action. It is whether the business has defined when that action is permitted and how an uncertain result is handled.

Separate understanding, proposing and executing

A system can classify a request, retrieve information and draft a response without having permission to change a booking. These are different levels of authority and should be designed separately.

In a first release, an assistant may produce a structured recommendation for an agent. The operator can verify the context, check the commercial detail and decide what happens next. That is a legitimate production workflow, not a failed attempt at full autonomy.

Classify actions by consequence

Routine information retrieval may need fewer controls than a cancellation, refund, fare change or payment action. The right boundary depends on your operation, but the policy should be explicit and testable.

For each action, define who can approve it, what evidence they must see and when the approval expires. If the quote or booking state changes after approval, the system should not assume the earlier decision is still valid.

Treat messages and documents as untrusted input

OWASP identifies excessive agency as a risk when language-model systems have too much functionality, permission or autonomy. Its mitigation guidance supports limiting what tools can do and introducing appropriate approval.

For travel workflows, customer messages and retrieved content should not be able to grant new permissions or override the operating policy. Enforce authority in the application and tool layer, rather than relying only on a sentence in a model prompt.

Design a review that a busy agent can use

An approval request should show the intended action, the affected record, the source of commercial information and what will change. Avoid asking someone to approve a long conversation without a concise decision summary.

Make rejection and correction first-class actions. The operator should be able to explain what is wrong, return the work for more information and continue manually. A queue that allows only approve or abandon will push staff toward workarounds.

Record outcome, not just intent

After an approved action, distinguish the request being sent from the supplier confirming it. Record the response and expose pending or failed states. Do not tell the traveller the change is complete merely because a tool was called.

Define recovery before expanding authority: who investigates an uncertain result, how duplicate actions are avoided and what information the next agent receives. Test these cases with operational staff, not only the engineering team.

A sensible first pilot

Choose one repetitive workflow with a named owner and a clear approval boundary. Evaluate the quality of assembled information, approval turnaround, rejection reasons and the accuracy of confirmed outcomes.

Broader automation can follow evidence from those tests. The objective is less repetitive work with accountable control—not the highest possible number of autonomous actions.

Sources & further reading

External sources support the specific industry context referenced in this guide. The workflow recommendations are Appnox’s proposed approach, not claims of industry-wide results.

Start with a conversation

One workflow. Twenty minutes. A clearer next step.

Discuss your travel or hospitality operation with a solutions architect. Explore the options and whether a deeper review would help.

Free · 20 minutes · No obligation to commission an audit