State model
A durable saga record owns step status, retries, deadlines, compensation and custody. Source systems retain legal business state.
A model trace does not prove what authority was checked, what action executed or whether the intended business effect actually occurred.
The ledger links request, context fingerprint, policy result, human approval, action receipt, readback and outcome verification into a reconstructable chain.
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.
Typed commands, state changes and receipts cross an event spine without surrendering domain ownership.
Permitted workThe platform supplies reusable controls and contracts. Domain teams retain business logic, data purpose and outcome ownership.
Consistency ruleTie deployed code, prompt, model, data, permissions, policy and evidence to one release manifest and compatibility graph.
Hard boundaryThe model is not a system of record, identity provider, policy authority or proof that an external effect occurred.
The journey can change account, payment, case or document state across systems that do not share one transaction boundary.
Receipts are append-only, version-qualified and independent of generated narrative; unknown outcomes remain explicit operational states.
A deterministic outer workflow contains model-led work inside typed, observable calls. Dashed messages remain proposals until policy or a human grants authority.
A durable saga record owns step status, retries, deadlines, compensation and custody. Source systems retain legal business state.
Mutating calls pass through typed capability contracts. Events notify downstream services, but command acceptance and effect readback remain distinct.
Use idempotent local transactions and eventual cross-system consistency. Unknown outcome is a first-class state, not an exception hidden by retry.
These roles are deliberately vendor-neutral. Each can be independently owned, versioned and replaced.
Evaluates identity, purpose, capability, amount, risk tier and policy version; returns allow, deny, step-up or human-review with reasons.
Exposes typed, allow-listed capabilities with schema validation, delegated identity, idempotency, timeout semantics and effect readback.
Appends request, versions, policy result, model proposal, approval, action receipt, readback, correction and custody events under one correlation key.
Classifies unknown outcomes, replays idempotent work, runs compensations and restores from the last verified checkpoint.
Durable records carry provenance, authority, effect and custody without turning a transcript into an uncontrolled memory store.
Tie deployed code, prompt, model, data, permissions, policy and evidence to one release manifest and compatibility graph.
The selected design is not universally superior. It is the safer fit for this boundary and failure cost.
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.
Use direct calls for narrow same-domain reads; mediate cross-domain, reusable or mutating capabilities.
Force every call through one integration pattern.
Cost acceptedMediation adds a hop and ownership overhead; direct calls increase coupling and duplicate controls.
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.
Use local commits, idempotent steps, compensations and an unknown-outcome state.
Attempt one atomic transaction across independent banking systems.
Cost acceptedSagas expose temporary inconsistency and require recovery logic, but fit systems that cannot share one transaction boundary.
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_action_rate = requests_per_second x steps_per_requestreconciliation_load = timed_out_actions + mismatched_readbacksrecovery_capacity = open_unknown_outcomes / owner_resolution_rateEnforce purpose, tenant and workload identity at every hop; telemetry stores metadata rather than unrestricted prompts or payloads.
A design is production-ready only when teams can prove what happened, recover it and change it safely.
reachable-authority analysis
cross-version compatibility
failure and rollback rehearsal
cost, latency and trace attribution
Request, authority decision, approval, idempotency key, action receipt, readback, reconciliation and verified outcome.
Service and control owners define retention, review exceptions and accept operating evidence.
Automate reversible steps first. Expand authority only after duplicate, timeout, compensation and operator-recovery tests pass under peak load.
Platform, domain product, data, security, model-risk and service owners share certification decisions.