Healthcare: Medical Record Summarization with Claude Code: Sandbox Policy

A production playbook for medical record summarization in healthcare operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.

Audience: Healthcare admin teams preparing case reviews

The problem

Healthcare admin teams preparing case reviews need medical record summarization to run repeatedly against clinical notes, discharge summaries, lab reports, and referral documents. In healthcare operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Run medical record summarization 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 medical record summarization, 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