State model
Append-only case events feed a current-state projection. Evidence rows keep source, observation time, validity, correction history and narrative usage.
A locked-out customer may have changed device, phone number and location at the same time, making ordinary recovery signals unreliable.
A recovery workflow assembles independent identity evidence, scores contradiction rather than familiarity, and offers only the recovery route permitted by current risk policy.
Organisations, systems and operating conditions are intentionally anonymised and recomposed. The design demonstrates engineering and banking-domain reasoning; it does not represent a named client estate, vendor product or measured production result.
A shared authority core coordinates independently owned capability cells, domain systems and operating evidence.
Permitted workThe experience layer may explain, collect and route. Authentication, customer records and irreversible servicing remain independently controlled.
Consistency ruleBind every turn to the authenticated subject and current journey; re-evaluate when channel, device, consent or custodian changes.
Hard boundaryThe model is not a system of record, identity provider, policy authority or proof that an external effect occurred.
An alert or case requires evidence fan-out, deterministic triage, residual model reasoning and a defensible human disposition.
The model proposes evidence gaps but cannot lower an authentication requirement or issue a credential.
A deterministic outer workflow contains model-led work inside typed, observable calls. Dashed messages remain proposals until policy or a human grants authority.
Append-only case events feed a current-state projection. Evidence rows keep source, observation time, validity, correction history and narrative usage.
Use asynchronous ingestion and bounded parallel reads. Slow providers have independent timeout and circuit-breaker policy so one source cannot exhaust the case tier.
Pin policy and evidence versions at case open. Later corrections append and may trigger reassessment; they do not rewrite the historic basis silently.
These roles are deliberately vendor-neutral. Each can be independently owned, versioned and replaced.
Returns candidate entities and typed relationships with match features, contradictions, effective dates and non-merge evidence.
Evaluates identity, purpose, capability, amount, risk tier and policy version; returns allow, deny, step-up or human-review with reasons.
Runs a versioned state machine with explicit waits, deadlines, retries, compensations, human tasks and terminal states.
Presents claims beside evidence, alternatives, uncertainty, missing information, permitted actions and current custody.
Appends request, versions, policy result, model proposal, approval, action receipt, readback, correction and custody events under one correlation key.
Durable records carry provenance, authority, effect and custody without turning a transcript into an uncontrolled memory store.
Bind every turn to the authenticated subject and current journey; re-evaluate when channel, device, consent or custodian changes.
The selected design is not universally superior. It is the safer fit for this boundary and failure cost.
Bias consequential journeys against false merge and retain unresolved candidates.
Automatically merge the highest-scoring candidate.
Cost acceptedMore cases require clarification, but one person's authority or risk cannot silently attach to another.
Compile stable decision logic and retain retrieval for explanation and residual ambiguity.
Ask a model to interpret the source document for every request.
Cost acceptedRule compilation needs controlled change, but creates repeatable decisions, regression tests and clear exceptions.
Keep consequential state transitions deterministic and use models inside bounded steps.
Let the model choose the complete path and recovery sequence.
Cost acceptedThe shell reduces flexibility, but makes deadlines, retries, permissions and recovery testable.
Keep people at irreversible, ambiguous and policy-exception points; sample lower-risk automated outcomes independently.
Require the same manual approval at every step.
Cost acceptedRisk-tiering reduces review load but needs calibrated thresholds, sampling and immediate withdrawal of authority when drift appears.
Use append-only events plus a rebuildable current-state projection.
Overwrite the case row with its latest status.
Cost acceptedReplay and storage are more complex, but point-in-time reconstruction and correction lineage remain possible.
Retries are bounded by knowledge of business effect; unknown outcome remains visible, owned and independently reconciled.
Actual thresholds belong to accountable service owners. The design exposes the equations and observables that those owners must baseline.
peak_enrichment_qps = peak_case_rate x sources_per_casereview_hours = residual_cases / investigator_throughputevidence_storage = cases x evidence_rows x retention_windowMinimise transcript reuse, isolate sensitive support data and expire transient context independently of the case record.
A design is production-ready only when teams can prove what happened, recover it and change it safely.
channel and identity transition test
accessible communication and vulnerability test
handoff rejection and custody timeout test
context minimisation review
Signal provenance, contradiction matrix, policy result, challenge outcomes, reviewer decision and credential receipt.
An identity specialist authorises exceptional recovery and records the basis.
Use shadow decisions and blind samples before allowing deterministic closes. Keep agent-touched cases under human disposition until operating evidence supports narrower review.
Journey, identity, accessibility, servicing operations and records owners share the operating decision.