Travel Disruption Claim Review with Claude Code: Sandbox Policy

A production playbook for travel disruption claim review in travel operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.

Audience: Travel and airline operations teams

The problem

Travel and airline operations teams need travel disruption claim review to run repeatedly against itineraries, delay records, receipts, policies, and customer messages. In travel operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Run travel disruption claim review in an ephemeral sandbox, keep provider credentials in the broker, expose narrow tools, and store logs outside the workspace for review.

Tradeoffs and failure modes

A narrower runtime blocks ambient machine behavior, but it gives security reviewers a concrete boundary. For travel disruption claim review, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.

Runtime boundary

filesystem: /skill and /skill/.argo/inputs only
network: deny by default
artifacts: /skill/output/artifacts
logs: retained outside sandbox
provider: Claude Code

Run this on Argo