Agent Evaluation Suite with Claude Code: Sandbox Policy
A production playbook for agent evaluation suite in cross-industry operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.
Audience: AI quality teams
The problem
AI quality teams need agent evaluation suite to run repeatedly against eval cases, expected outputs, logs, and scoring rubrics. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Run agent evaluation suite 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 agent evaluation suite, 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