Run Output Validation with Claude Code: Artifact Delivery
A production playbook for run output validation in cross-industry operations using Claude Code: artifact delivery, run-scoped inputs, logs, typed results, and artifacts.
Audience: AI platform teams
The problem
AI platform teams need run output validation to run repeatedly against result JSON, artifacts, logs, and acceptance 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
Require Claude Code to write customer-visible files under /skill/output/artifacts, validate filenames and sizes, then return signed artifact metadata in argo.result.v1.
Tradeoffs and failure modes
Artifact policy constrains file output, but customers receive files that are durable, typed, and safe to download. For run output validation, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Artifact manifest
artifacts:
- run-output-validation-summary.md
- run-output-validation-evidence.csv
- run-output-validation-review.json
signed_urls: true
retention: org_policy
Run this on Argo