Home · Work · System design
Assurance, observability and economicsAnalytical decision supportfederated

Decision-route value attribution

A lower handling cost or shorter conversation does not prove that an AI route improved customer, control or operational outcomes.

Approach

The measurement design links route choice to service quality, rework, loss, complaints, control exceptions, human effort and delayed outcomes using comparable cohorts and explicit attribution limits.

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.

Overview

System overview

A shared authority core coordinates independently owned capability cells, domain systems and operating evidence.

Decision-route value attribution: federated system architecture A federated architecture separates channels, a shared authority core, independently deployed capability cells, domain systems of record, and an evidence and operations rail. Calls use scoped identity and typed contracts; every decision path emits a receipt. aSystem boundary and decision authoritySchematic architecture · illustrative scenario Channels and operatorsFederated capability cellsDomain systemsEvidence, recovery and operations Customer channelweb · mobile · voice Staff workspacereview · approve Service eventbatch · stream · API Operations consoleincident · replay Scope & authority coreidentity · purpose · policy Domain adapter meshversion · health · readback Party RelationshipResolverIdentity & relationshipsDecision Receipt LedgerEvidence & auditBehaviour EvaluationHarnessEvaluation & releaseOperational Read ModelWorld state & read modelsAuthority Rules EngineAuthority & policyEvidence ContextCompileravailable, not admittedJourney StateCoordinatoravailable, not admittedTyped Action Brokeravailable, not admittedDistributed tracesauthoritative recorddecisionauthoritative recordeffect logsauthoritative recordevaluation resultsauthoritative record Decision receipt archiveappend-onlyTrace & cost pipelineredacted telemetryRecovery & custody queueowned exceptionsRelease & rollback registrysigned manifest
Figure 1. Independent capability cells share an authority membrane without sharing domain ownership. Source-specific behaviour remains behind adapters and every decision emits operating evidence. This is an illustrative system model, not a named deployment.

Permitted workThe assurance layer observes and evaluates; it may trigger a stop or review but cannot redefine business policy from telemetry alone.

Consistency ruleCarry one correlation chain across synchronous and asynchronous hops and separate event occurrence from observation and processing time.

Hard boundaryThe model is not a system of record, identity provider, policy authority or proof that an external effect occurred.

Deployment

Deployment

A business operator needs a reconciled view, explanation or scenario from several data products while retaining ownership of the business decision.

Decision-route value attribution: deployment and trust-zone topology A production topology separates public edge, identity boundary, workload cluster, integration plane, data enclave and operating controls. Connections name transport and identity protocols, and a second region provides controlled failover. bDeployment topology and failure domainsLogical deployment · no measured estate data EDGE AND ACCESS PRIVATE WORKLOAD CLUSTER INTEGRATION AND DATA ENCLAVE OPERATIONS, EVIDENCE AND RECOVERY PLANE Web applicationfirewallTLS · bot · rate API ingressschema · quota Identity brokerOIDC · MFA Purpose gateclaims · consent HTTPStokensubject Regional traffic managerhealth · canary · failover Workload identity issuershort-lived service tokens Event & work queuepartition · DLQ · backpressure Secrets & key serviceenvelope encryption · rotation PartyRelationship…zonal workloadAuthority RulesEnginezonal workloadDecision ReceiptLedgerzonal workloadBehaviourEvaluation…zonal workloadOperational ReadModelzonal workloadReserved workloadslotdisabledReserved workloadslotdisabledReserved workloadslotdisabled HTTPS · scoped JWT workload token async eventkey lookup IntegrationgatewaymTLSDistributed tracessystem of recorddecisionsystem of recordeffect logssystem of recordevaluation resultssystem of record Model route enclavepolicy · schema · egress Qualified data storesSQL · graph · object Trace, metric & cost pipelineOpenTelemetry · redaction Decision receipt archiveappend-only · retention Reconciliation workersreadback · replay · DLQ On-call & review queuescustody · SLA · escalation Secondary-region standbycompatible manifest telemetryreceiptsexceptions
Figure 2. Workloads remain isolated from systems of record. Short-lived identity, typed integration contracts, append-only evidence and controlled failover define the deployable boundary; the topology is schematic.
Authority checkpoint

Metrics are segmented by risk and journey complexity; the system cannot claim causality from simple before-and-after movement.

Runtime

Runtime flow

A deterministic outer workflow contains model-led work inside typed, observable calls. Dashed messages remain proposals until policy or a human grants authority.

Decision-route value attribution: runtime sequence and control branches Ten lifelines and eighteen protocol messages show authentication, evidence acquisition, policy authority, bounded reasoning, effect verification, human review and append-only evidence. A shaded branch contains timeout and unknown-outcome handling. cRuntime protocol and control pointsProtocol model · illustrative execution Channelcustomer or staffAccess gateidentity & purposeCoordinatorworkflow ownerContextqualified evidenceAuthoritypolicy decisionReasonerbounded inferenceAction brokertyped capabilitySource estateauthoritative stateReview deskhuman decisionReceiptledgerappend-only proof ALT · timeout, rejection, or unknown business effect No blind retry. Resolve source state, narrow the result, or retain custody. Material evidence missing → review queueUnknown effect → readback and reconciliationAuthority denied or expired → stop before dispatch HTTPS · request envelopeOIDC claims · purpose · deadlinetyped evidence requestREST/gRPC reads at qualified timefacts · validity · source versioncontext manifest · exclusionsauthority decision · conditionsminimal residual · closed schemacited proposal · confidence flagsexact capability and payload hashsigned grant · expiry · limitsidempotent command or readaccepted status · effect referenceindependent state readbackaction/effect receiptcase pack when review is requireddisposition · rationale · custodyqualified response · limitations authoritative callproposal / reviewevidence writePattern: Analytical decision support
Figure 3. The protocol separates request acceptance, permission, business effect and independent readback. A timeout first changes the knowledge state; it does not automatically justify another call. The paths are protocol semantics, not an observed production trace.
S

State model

A decision snapshot binds period, entity hierarchy, measures, formula versions, assumptions and source cut-offs. Scenarios never overwrite actuals.

I

Integration choice

Read from curated analytical products rather than operational tables. Use drill-through links for source detail and typed write-back only for approved decisions.

C

Consistency semantics

Definitions and units are resolved before aggregation. Missing data stays missing; mixed grains and double-counted entities fail reconciliation.

Services

Services and interfaces

These roles are deliberately vendor-neutral. Each can be independently owned, versioned and replaced.

  1. ERG
    Identity and relationships

    Party Relationship Resolver

    Returns candidate entities and typed relationships with match features, contradictions, effective dates and non-merge evidence.

    Degraded routePreserve separate candidates and route ambiguity for review. Never collapse entities simply to complete the journey.
  2. DES
    Evidence and audit

    Decision Receipt Ledger

    Appends request, versions, policy result, model proposal, approval, action receipt, readback, correction and custody events under one correlation key.

    Degraded routeBlock a consequential close when mandatory evidence is missing; keep the case open with an explicit evidence defect.
  3. SEL
    Evaluation and release

    Behaviour Evaluation Harness

    Runs component, route, trajectory, failure, harm and outcome tests against the versioned system manifest.

    Degraded routeReduce or withdraw authority when a dependency changes or a critical suite fails; preserve the last approved route where compatible.
  4. OSR
    World state and read models

    Operational Read Model

    Builds time-qualified projections from source events and reconciliations without becoming the legal system of record.

    Degraded routeExpose source lag and fall back to direct reads for defined critical facts; never present missing feeds as zero.
  5. PDS
    Authority and policy

    Authority Rules Engine

    Evaluates identity, purpose, capability, amount, risk tier and policy version; returns allow, deny, step-up or human-review with reasons.

    Degraded routeFail closed for effects and restricted data. Read-only explanation may continue only from approved public or customer-visible sources.
Figure 4. Each service exposes a typed contract and a defined degraded route. Coordination stays in the control plane while domain ownership remains outside it.
Data

Data and records

Durable records carry provenance, authority, effect and custody without turning a transcript into an uncontrolled memory store.

Decision-route value attribution: state ownership and evidence lineage Authoritative source observations feed six versioned runtime records. Each record names a single write owner. An append-only event and evidence stream builds a disposable current-state projection and supports audit replay. dState lineage, ownership and temporal validityLogical records · fields are illustrative AUTHORITATIVE INPUTS · POINT-IN-TIME QUALIFIEDDistributed tracessource version · observed atdecisionsource version · observed ateffect logssource version · observed atevaluation resultssource version · observed atqualified inputqualified inputqualified inputqualified input WRITE OWNER · Evidence Context CompilerRequest enveloperequest_idpurposeactor_refsubject_refversioned · attributable · retainedWRITE OWNER · Authority Rules EngineContext manifestcontext_idsource_refsource_versionobserved_atversioned · attributable · retainedWRITE OWNER · Typed Action BrokerCase statecase_idstatestate_versioncurrent_custodianversioned · attributable · retainedWRITE OWNER · Reasoning Route ManagerAuthority decisiondecision_idpolicy_versionrequested_capabilityoutcomeversioned · attributable · retainedWRITE OWNER · Behaviour Evaluation HarnessAction and effect receiptaction_ididempotency_keyinput_hashdispatch_statusversioned · attributable · retainedWRITE OWNER · Operational Read ModelCustody eventtransfer_idfrom_ownerto_ownerreasonversioned · attributable · retained APPEND-ONLY CASE EVENTS + DECISION RECEIPTSrequest hash · source versions · policy version · proposal · authority · effect readback · custody Operational current-state viewrebuildable projection
Figure 5. The record chain preserves source version, write ownership, authority and custody. Solid records are required in this scenario; dashed records remain compatible but dormant.
Consistency contractDomain source rule

Carry one correlation chain across synchronous and asynchronous hops and separate event occurrence from observation and processing time.

Choices

Trade-offs

The selected design is not universally superior. It is the safer fit for this boundary and failure cost.

  1. 01

    Optimise for fewer duplicate entities or fewer false merges

    Selected path

    Bias consequential journeys against false merge and retain unresolved candidates.

    Rejected path

    Automatically merge the highest-scoring candidate.

    Cost acceptedMore cases require clarification, but one person's authority or risk cannot silently attach to another.

  2. 02

    Mutable current-state record or append-only decision history

    Selected path

    Use append-only events plus a rebuildable current-state projection.

    Rejected path

    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.

  3. 03

    Evaluate model responses alone or certify the complete reachable system

    Selected path

    Test prompts, models, tools, knowledge, policies, state transitions and human paths together.

    Rejected path

    Use a static answer-quality benchmark as the release gate.

    Cost acceptedSystem evaluation takes longer and needs synthetic environments, but detects authority and recovery failures that answer scoring misses.

  4. 04

    Query every source in the critical path or maintain operational read models

    Selected path

    Use event-fed projections for scale and direct readback for consequential effects.

    Rejected path

    Fan out to all systems of record for every interaction.

    Cost acceptedRead models introduce lag and reconciliation work, but reduce source load and make cross-system views feasible.

  5. 05

    Reason over policy text at runtime or compile executable rules

    Selected path

    Compile stable decision logic and retain retrieval for explanation and residual ambiguity.

    Rejected path

    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.

Figure 6. Teal marks the selected route; coral dotted rules preserve the rejected alternative. Each decision states the cost accepted rather than presenting one architecture as universally superior.
Recovery

Failures and recovery

Retries are bounded by knowledge of business effect; unknown outcome remains visible, owned and independently reconciled.

Decision-route value attribution: failure classification and recovery control flow Five failure sources converge on a classifier that distinguishes known no effect, known failure, unknown outcome, material evidence gaps and control-plane failure. Each state has an explicit recovery route, service degradation and evidence receipt. eFailure classification and recovery policyControl model · thresholds set by owners DETECTION POINTSEFFECT CLASSIFIERRECOVERY DECISIONSERVICE-SPECIFIC DEGRADATION Source dependencyAutomation can move effort downstream…Authority servicePolicy is unavailable, expired, or returns…Reasoning routeOutput fails schema, citation, grounding…Action pathTransport times out after dispatch & the…Evidence railReceipt or custody append fails after a… Outcome classifierattempt · idempotency · source readback ·… Known no effectSafe bounded retry with the same…Known failureNarrow, queue, compensate, or fail closed…Unknown outcomeRead back authoritative state before retry…Material evidence gapRetain custody & create an owned…Control-plane failureStop promotion or dispatch; restore the…Party Relationship ResolverPreserve separate candidates &route ambiguity for review. Nevercollapse entities simply to…Decision Receipt LedgerBlock a consequential close whenmandatory evidence is missing;keep the case open with an…Behaviour Evaluation HarnessReduce or withdraw authority whena dependency changes or a criticalsuite fails; preserve the last…Operational Read ModelExpose source lag & fall back todirect reads for defined criticalfacts; never present missing feeds…Authority Rules EngineFail closed for effects &restricted data. Read-onlyexplanation may continue only from… RECOVERY RECEIPTfault origin · classification basis · owner · retry/compensation key · readback reference · residual risk · resolved at classifier evidencerecovery evidence Pattern rule: Quarantine affectedmeasures, preserve the lastqualified snapshot where…
Figure 7. Recovery follows the known business-effect state, not the transport symptom. Every branch ends in a receipt preserving fault origin, custody and reconciliation basis.
Capacity

Performance and capacity

Actual thresholds belong to accountable service owners. The design exposes the equations and observables that those owners must baseline.

Dependent variablesOperating
envelope
  • reconciliation coverage
  • query and scenario latency
  • lineage completeness
  • downstream decision and rework outcomes
Capacity relationships
  1. 01query_load = active_users x decisions_per_hour x source_scans
  2. 02scenario_work = entities x periods x assumptions x alternatives
  3. 03review_value = avoided_rework + decision_gain - compute - human_effort
Privacy lens

Collect the minimum diagnostic metadata, tokenise subjects and keep raw prompts or case evidence behind stricter access and retention.

Figure 8. The variables define what must be measured before capacity or quality claims can be accepted. Relationships are analytical scaffolds, not invented targets or production results.
Operations

Release and operations

A design is production-ready only when teams can prove what happened, recover it and change it safely.

Minimum release gates
  1. 01

    trace and outcome completeness

  2. 02

    control-bypass and false-negative review

  3. 03

    cost and human-effort attribution

  4. 04

    kill-switch and recovery exercise

Figure 9. Promotion requires evidence at each gate and a compatible rollback route. No gate is implied to have passed; accountable owners set thresholds and sign the record.
Operating stateReleaseRecover
Evidence

Route assignment, cohort definition, customer and control outcomes, downstream work, cost model, confidence limits and owner interpretation.

Human authority

Finance, product, operations and risk owners agree the attribution method and decide investment.

Evolution

Begin with explanation and transparent calculations. Add recommendation only where decision rights, counterfactual evaluation and outcome measurement are established.

Ownership

Service, control, finance, model, data and operations owners interpret evidence and decide intervention.

Figure 10. Evidence, human authority, ownership and controlled evolution remain coupled throughout operation. Removing any quadrant breaks the assurance case.