Skip to main content

SOC 2 Type II for AI agents

2026 SOC 2 questionnaires carry 15–20 agent-specific items: prompt logging retention, model versioning, sub-processor LLM chain, hallucination handling, agent decision lineage. Generic CC7 logging does not satisfy these.

Mapping Ujex to the agent-specific SOC 2 items

SOC 2 agent itemUjex source
Prompt logging retention ≥ 12 monthsAudit payload.action includes prompt-bearing actions; retention default 12mo
Model versioningaat.agent_version on every row
Sub-processor LLM chainmeta.model + meta.vendor stamped by Budgets preflight
Agent decision lineageaat.parent_record_id chains approve → act → write
Hallucination handlingAudit row on every overridden / corrected output; Approvals decisions linked
Tenant isolationPods + Security Rules ownership check
Tool authorizationSigned tool manifests, server-side policy, server-injected credentials, and Budgets preflight

Audit evidence

Use auditExportAATBundle over the auditor's window. The bundle includes the chain head hash so the auditor can verify completeness independently using ujex-audit-chain.

What's NOT covered

  • Annual penetration test
  • Vendor risk management on your own LLM provider (OpenAI / Anthropic / GCP)
  • Background checks / personnel security
  • Physical security of your on-prem deployment

Ujex provides the technical artefacts the agent-specific SOC 2 items demand; the rest of the SOC 2 program is the operator's.