Jude Dialog · Jude Dialog · tok-5da025b3b6763f883c1a42ade90c565f
Adversarial: corrupt t6
P03: Failure compounds from turn 6 (turn 6)
Plays a synthetic caller against Jude through the public address and checks the outcome against the ledger.
Requirement
Turn 6 arrives as line noise; Jude asks again and no state changes
Target that exceeds PolyAI
A corrupted turn 6 changes no state (state hash before = after) and the conversation still verifies
Regulation
FCA PRIN 2A (Consumer Duty); UK GDPR arts 22A-22D; EU AI Act art 50
Steps
- Caller opens Calls (voice) and the first turn discloses an AI agent
- Caller states the need in Cymraeg
- Policy gates run in code: clinical red flag, vulnerability, verification before account data, strong customer authentication bound to amount and payee
- Only backend records are read and only their fields are stated (billing, faq)
- Confirmation asked before any change; a yes spoken over the question is not taken
- Change written once (idempotency key) and receipted
- Outcome verified against the ledger; receipt chain verified
Cases
| Kind | Given or injected | Then |
|---|---|---|
| happy path | a simulated customer of Jude Bank with an account, a bill and two orders | Turn 6 arrives as line noise; Jude asks again and no state changes |
| receiving side | the ledger, ticket queue or diary holds the record stated in the conversation, with the same reference in the receipt | |
| failure path | backend timeout on the next backend call | the data is said to be not reachable, no fact is stated, the call is retried; a second miss hands over with a reference |
| failure path | the turn arrives as line noise | the question is asked again; the receipt state hash is unchanged |
| failure path | the same message arrives twice | the stored answer is returned; nothing is done twice |
| independent re-run | a different ATBAN agent reproduces the verified outcome |
Linked estate journeys
stb-041, wf.bank-010, wf.bank-028
Frozen contract 2026-10-23 · sha256 03611b159ef0845477033c56303e8aaac7573cc871e3344dd81f9a77c81742fb