End to end architecture from ingestion to compliance dashboard

Plain language meaning

End to end architecture from ingestion to compliance dashboard shows how a bank connects source systems, governed data, feature generation, model services, human review, decision logging, monitoring and compliance reporting into one controlled AI operating model.

This topic is about banking AI architecture and control design across the full lifecycle. It is not about drawing a generic technology stack without banking obligations.

In a real bank, this is not a loose technology idea. It is a controlled operating step where customer facts, banking policy, model behaviour, human authority, legal obligations and retained evidence must line up. AI and ML can improve speed, consistency and detection quality, but the bank must still prove why the process was fair, explainable, secure, monitored and fit for purpose.

Where it sits in the banking AI journey

This card belongs to The Complete Pipeline. The working flow is Source systems, Governed data layer, Feature and model services, Human decision workflow, and Compliance dashboard.

Read the flow as a banking control journey. Each stage needs a source system, a decision purpose, a failure mode, a control owner, a fallback path, a customer-impact view and retained evidence. Without those elements, the bank may have automation, but it does not yet have a bank-grade AI process.

Banking data and evidence

The important data points are source lineage, consent status, quality score, feature snapshot, model output, decision log, control status, and dashboard metric. These items matter because they influence lending eligibility, affordability, fraud risk, compliance treatment, operational queueing, regulatory reporting, customer explanation and audit traceability.

The evidence pack should include lineage map, data-quality report, feature version, model inventory entry, review workflow log, control test, and compliance dashboard export. A strong bank can replay the case from source data to feature values, model output, control result, human review, final outcome and monitoring result. A weak bank only knows that a system produced an answer.

Controls that make AI adoption safe

The core controls are data governance, access control, model inventory, API resilience, workflow ownership, control monitoring, and dashboard attestation. These controls make the topic bank-grade because they tie technical output to approved policy, legal obligations, model governance, operational resilience and management accountability.

AI can help compare records, detect anomalies, retrieve policy, summarise case evidence, prioritise work, highlight weak signals and improve investigator consistency. It should not invent missing facts, ignore failed checks, bypass authority, hide uncertainty, decide material customer outcomes without approval or create explanations that cannot be tied back to approved sources.

Regulatory and governance lens

For banking use cases, model risk, fair lending, adverse-action explanation, credit-risk governance, data lineage, operational resilience, AML/CFT risk-based controls, sanctions compliance, fraud information sharing and auditability can meet in the same workflow. The practical design must therefore be narrower and more disciplined than a generic AI design.

The practical test is simple: if a reviewer asks why the bank used the data, why the model output was trusted, why the customer received that action, why an alert was cleared, why an exception was approved, or why a regulatory record was prepared, the evidence must already exist.

Diagram walkthrough

Read the diagram from left to right as Source systems, Governed data layer, Feature and model services, Human decision workflow, and Compliance dashboard. The diagram is a control map, not decoration. It shows the minimum route by which data, AI or ML output, human action and audit evidence should connect.

Use it as a 30-minute study method. For each box, ask what system produces the data, what can go wrong, what control detects the weakness, who reviews the case, what customer or regulatory impact could arise and what record proves closure.

Most important mistake to avoid

The common failure is presenting AI architecture as only ingestion, model and dashboard. A banking architecture must also show ownership, authority, validation, exceptions, resilience, customer impact and audit evidence.

The correction is to slow down the thinking, not necessarily the process. A well-designed banking AI process can be fast, but every fast step must still leave behind source lineage, control evidence, decision reason, human accountability, monitoring data and issue ownership.

Source anchors for accurate study

Federal Reserve SR 26-2, dated 17 April 2026, supersedes SR 11-7 and SR 21-8 for traditional model risk management and clarifies that generative and agentic AI need governance through broader risk-management controls.

NIST AI RMF 1.0 uses Govern, Map, Measure and Manage functions for AI risk management, and NIST AI 600-1 adds generative-AI risk actions for content provenance, hallucination, data protection, cybersecurity and human oversight.

U.S. Regulation B, 12 CFR 1002.9, requires specific principal reasons for adverse action in covered credit decisions, including when a creditor uses an AI model. CFPB Circular 2022-03 was withdrawn on 12 May 2025; do not cite it as current guidance. Primary sources: https://www.consumerfinance.gov/rules-policy/regulations/1002/9 and https://www.consumerfinance.gov/compliance/guidance/withdrawn-guidance/.

The EU AI Act treats AI systems used to evaluate creditworthiness or establish credit scores for natural persons as high-risk, except certain fraud detection and prudential capital contexts.

The Basel Framework IRB standards require banks to estimate and validate PD, LGD and EAD using relevant data, meaningful risk differentiation and ongoing governance.

FFIEC BSA/AML examination guidance expects suspicious activity monitoring systems to be risk-based, explainable by management, periodically reviewed and independently validated where appropriate.

Federal Reserve SR 26-3 and FinCEN's 12 June 2026 Section 314(b) materials clarify fraud-related information sharing under the USA PATRIOT Act safe-harbor framework for participating financial institutions.

OFAC's Framework for Compliance Commitments describes sanctions compliance programme components including management commitment, risk assessment, internal controls, testing and auditing, and training.

Banking practice note: customer purpose

For end to end architecture from ingestion to compliance dashboard, customer purpose is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from source lineage to lineage map. Then ask which control from data governance proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

AI can assist by comparing records, detecting unusual patterns, retrieving approved policy, summarising weak evidence, prioritising exceptions and preparing review notes. The bank should not allow a generated explanation, a confident score or a convenient dashboard to replace validation, consent, human judgement, customer communication, regulatory judgment or issue closure.

A strong implementation records the source event, data timestamp, consent or lawful basis, model or prompt version, feature values, score or generated output, threshold, reason code, user action, exception status, monitoring result, owner review and final outcome. That record lets risk, compliance, audit, technology and operations speak from the same facts.

Banking practice note: consent and lawful use

For end to end architecture from ingestion to compliance dashboard, consent and lawful use is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from consent status to data-quality report. Then ask which control from access control proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: source lineage

For end to end architecture from ingestion to compliance dashboard, source lineage is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from quality score to feature version. Then ask which control from model inventory proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: KYC and identity

For end to end architecture from ingestion to compliance dashboard, KYC and identity is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from feature snapshot to model inventory entry. Then ask which control from API resilience proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: account behaviour

For end to end architecture from ingestion to compliance dashboard, account behaviour is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from model output to review workflow log. Then ask which control from workflow ownership proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: feature freshness

For end to end architecture from ingestion to compliance dashboard, feature freshness is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from decision log to control test. Then ask which control from control monitoring proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: point-in-time correctness

For end to end architecture from ingestion to compliance dashboard, point-in-time correctness is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from control status to compliance dashboard export. Then ask which control from dashboard attestation proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: model version

For end to end architecture from ingestion to compliance dashboard, model version is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from dashboard metric to lineage map. Then ask which control from data governance proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: decision threshold

For end to end architecture from ingestion to compliance dashboard, decision threshold is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from source lineage to data-quality report. Then ask which control from access control proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: reason code

For end to end architecture from ingestion to compliance dashboard, reason code is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from consent status to feature version. Then ask which control from model inventory proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: human review

For end to end architecture from ingestion to compliance dashboard, human review is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from quality score to model inventory entry. Then ask which control from API resilience proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: fraud control

For end to end architecture from ingestion to compliance dashboard, fraud control is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from feature snapshot to review workflow log. Then ask which control from workflow ownership proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: sanctions control

For end to end architecture from ingestion to compliance dashboard, sanctions control is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from model output to control test. Then ask which control from control monitoring proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: AML control

For end to end architecture from ingestion to compliance dashboard, AML control is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from decision log to compliance dashboard export. Then ask which control from dashboard attestation proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: fair lending

For end to end architecture from ingestion to compliance dashboard, fair lending is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from control status to lineage map. Then ask which control from data governance proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: regulatory reporting

For end to end architecture from ingestion to compliance dashboard, regulatory reporting is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from dashboard metric to data-quality report. Then ask which control from access control proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: operational exception

For end to end architecture from ingestion to compliance dashboard, operational exception is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from source lineage to feature version. Then ask which control from model inventory proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: customer harm

For end to end architecture from ingestion to compliance dashboard, customer harm is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from consent status to model inventory entry. Then ask which control from API resilience proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: audit trail

For end to end architecture from ingestion to compliance dashboard, audit trail is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from quality score to review workflow log. Then ask which control from workflow ownership proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: data quality

For end to end architecture from ingestion to compliance dashboard, data quality is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from feature snapshot to control test. Then ask which control from control monitoring proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: privacy minimisation

For end to end architecture from ingestion to compliance dashboard, privacy minimisation is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from model output to compliance dashboard export. Then ask which control from dashboard attestation proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: committee reporting

For end to end architecture from ingestion to compliance dashboard, committee reporting is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from decision log to lineage map. Then ask which control from data governance proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: reconciliation

For end to end architecture from ingestion to compliance dashboard, reconciliation is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from control status to data-quality report. Then ask which control from access control proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: exception ownership

For end to end architecture from ingestion to compliance dashboard, exception ownership is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from dashboard metric to feature version. Then ask which control from model inventory proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: monitoring cadence

For end to end architecture from ingestion to compliance dashboard, monitoring cadence is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from source lineage to model inventory entry. Then ask which control from API resilience proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: closure evidence

For end to end architecture from ingestion to compliance dashboard, closure evidence is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from consent status to review workflow log. Then ask which control from workflow ownership proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: policy retrieval

For end to end architecture from ingestion to compliance dashboard, policy retrieval is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from quality score to control test. Then ask which control from control monitoring proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: investigator feedback

For end to end architecture from ingestion to compliance dashboard, investigator feedback is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from feature snapshot to compliance dashboard export. Then ask which control from dashboard attestation proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: model drift

For end to end architecture from ingestion to compliance dashboard, model drift is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from model output to lineage map. Then ask which control from data governance proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: control attestation

For end to end architecture from ingestion to compliance dashboard, control attestation is not a side detail. It decides whether the bank can connect the AI or ML output to a real banking purpose, a real customer or regulatory outcome and a real accountable owner. Study the topic as a banking process first and a model process second.

Trace one item from decision log to data-quality report. Then ask which control from access control proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: customer purpose

Trace one item from control status to feature version. Then ask which control from model inventory proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: consent and lawful use

Trace one item from dashboard metric to model inventory entry. Then ask which control from API resilience proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: source lineage

Trace one item from source lineage to review workflow log. Then ask which control from workflow ownership proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: KYC and identity

Trace one item from consent status to control test. Then ask which control from control monitoring proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: account behaviour

Trace one item from quality score to compliance dashboard export. Then ask which control from dashboard attestation proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: feature freshness

Trace one item from feature snapshot to lineage map. Then ask which control from data governance proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: point-in-time correctness

Trace one item from model output to data-quality report. Then ask which control from access control proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: model version

Trace one item from decision log to feature version. Then ask which control from model inventory proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: decision threshold

Trace one item from control status to model inventory entry. Then ask which control from API resilience proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: reason code

Trace one item from dashboard metric to review workflow log. Then ask which control from workflow ownership proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: human review

Trace one item from source lineage to control test. Then ask which control from control monitoring proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: fraud control

Trace one item from consent status to compliance dashboard export. Then ask which control from dashboard attestation proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: sanctions control

Trace one item from quality score to lineage map. Then ask which control from data governance proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: AML control

Trace one item from feature snapshot to data-quality report. Then ask which control from access control proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Banking practice note: fair lending

Trace one item from model output to feature version. Then ask which control from model inventory proves the item was complete, current, authorised, relevant and fit for use. If that trace cannot be shown without manual guessing, the process is not yet bank-grade.

Trace one transaction across boundaries

A source channel sends a payment instruction to a hub with a stable business ID. Event ingestion validates and enriches it, feature services produce point-in-time values, models return scores, and a policy layer applies fraud and mandatory compliance controls. The hub records the final action. Cases, settlement events and reporting flows follow afterward. At each boundary, preserve status, version, timestamp, owner and exception behavior. A model response is neither final settlement nor audit closure.

Run a deliberately broken path: beneficiary enrichment is stale, the fraud model returns a score, sanctions screening yields a candidate, and the hub deadline arrives. The orchestrator should reject invalid fraud input or use its approved restricted path while retaining the sanctions hold. Later source repair updates analytics without replaying payment commands. A dashboard should reconcile eligible instructions, scored and fallback decisions, holds, settlements, pending investigations and customer effects. Its drill-down must reach the original source and action evidence.