PUBLIC MVP DEMO

Veridom ACE Demo

Runtime control and evidence for agentic AI in regulated financial workflows.

This demo shows ACE intercepting a proposed AI-assisted credit action, evaluating it against configured autonomy boundaries, blocking execution where authority is unbound, and producing a verified per-decision evidence record.

Money-shot scenario
£650,000 credit action
Autonomous limit: £500,000
routing_stateASSISTED authority_binding_resultAUTHORITY_UNBOUND execution_permissionBLOCKED action_executedfalse trace integrityVERIFIED

01 — THE WORKING MVP

Boundary defined → Watchtower configured → scenario tested → policy exported → Gateway enforces → Evidence Console verifies.

The recording walks through the local ACE MVP surfaces: Boundary Studio-lite, ACE Gateway, and ACE Evidence Console.

02 — WHAT THE REVIEWER SHOULD SEE

One challenged AI-assisted action, controlled before execution and verified after the fact.

01

Boundary Studio — autonomy boundary configured

Credit actions may proceed autonomously only up to £500,000 when the configured Watchtower conditions allow it.

02

Scenario Tester — £650,000 proposed action

The test scenario asks ACE to evaluate a credit decision-support agent attempting a £650,000 action.

03

Gateway Result — ASSISTED / AUTHORITY_UNBOUND / BLOCKED

The action exceeds the autonomous boundary and no accountable actor is bound, so ACE blocks execution.

04

Evidence Console — sealed trace retrieved

The reviewer retrieves the sealed per-decision record showing boundary, authority, execution, policy, and trace fields.

05

Verification — trace integrity VERIFIED

The Console recomputes the SHA-256 trace hash and confirms the sealed record still matches the canonical payload.

03 — CURRENT STATUS

Current status

ACE is currently a working local MVP. It is not yet a production deployment. The current demo uses local SHA-256 trace verification, SQLite storage, policy hash binding, and a simulated credit decision-support workflow. Planned extensions include RFC 3161 timestamping, institutional signing, role-directory validation, authentication, and production deployment hardening.