Vendor Risk Review with Claude Code: API Runtime Pattern
A production playbook for vendor risk review in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Procurement and security teams
The problem
Procurement and security teams need vendor risk review to run repeatedly against vendor docs, SOC reports, DPAs, and questionnaire answers. 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 vendor risk review instructions as a skill, send vendor docs, SOC reports, DPAs, and questionnaire answers as run-scoped inputs, execute with Claude Code, 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 vendor risk 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=claude-code
workflow=vendor-risk-review
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo