Tenant Isolation Review with Codex: API Runtime Pattern
A production playbook for tenant isolation review in cross-industry operations using Codex: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: B2B SaaS security teams
The problem
B2B SaaS security teams need tenant isolation review to run repeatedly against tenant IDs, storage paths, logs, credentials, and auth checks. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the tenant isolation review instructions as a skill, send tenant IDs, storage paths, logs, credentials, and auth checks as run-scoped inputs, execute with Codex, poll terminal status, and consume argo.result.v1 instead of parsing a transcript.
Tradeoffs and failure modes
The API boundary forces the workflow to define inputs, terminal states, and result shape before customers depend on it. For tenant isolation review, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run request
POST /api/skills/<skill_id>/run
provider=codex
workflow=tenant-isolation-review
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo