Security Questionnaire Automation with Claude Code: API Runtime Pattern
A production playbook for security questionnaire automation in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Security and sales engineering teams
The problem
Security and sales engineering teams need security questionnaire automation to run repeatedly against questionnaires, evidence folders, and policy docs. 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 security questionnaire automation instructions as a skill, send questionnaires, evidence folders, and policy docs 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 security questionnaire automation, 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=security-questionnaire
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo