1.0
Preserve the decision chain
Audit entries connect the AI output, human decision, deterministic policy result, and final executor action.
- Proposal events
- Approval events
- Executor events
Home
Product
Audit log
Immutable evidence for proposals, approvals, rejections, policy versions, executor checks, and support actions.
Scope
Every action
Proposals and decisions are recorded together.
Filter
Entity
Trace by thread, customer, project, or actor.
Tone
Boring
Compliance infrastructure should be precise.
2.0
Useful during review
Teams can answer what happened, who approved it, what policy was in force, and what customer context was used.
- Actor metadata
- Before and after diffs
- Entity links
Operations
What this means in production.
These pages describe the product contract behind the UI, not a decorative brochure. Each surface should connect back to the same governed support loop.
Control boundary
Every side effect has an audit trail.
Operator workflow
Support moves through secure ingest, AI preparation, human approval, outbound execution, and audit evidence.
Configuration impact
Provider setup, project policies, knowledge trust, retention, and billing limits decide how this behaves for a real workspace.
Proof points
Designed for governed support, not hidden autonomy.
Every side effect has an audit trail.
Policy versions are visible.
Audit details stay workspace-scoped.
References
Official stack and legal references.
These external links point to provider documentation, privacy notices, data-processing terms, or platform terms that shape production operation.
Next