DataFab //  artificial proprietary intelligence T+00:00:00 ISO/IEC 27001:2022 · SOC 2 Type II — certified Raw egress  0 B 

DataFab  /  Utilities  /  Financial crime

Governed utility · banking, payments & financial services

The unit sees fragments. Give it one customer.

Core banking, payments, customer records, screening, trade finance, documents and a dozen vendor tools each hold a sliver of the truth — and none of them share an entity, a schema or a story. DataFab resolves them in place into one governed graph of customers, counterparties and money flow, then runs governed agencies over it from detection to defensible narrative.

Nothing migratedPerpetual, not periodicEvery disposition defensible

The brief

What you are actually being asked to do

“Clear the backlog. Cut the false positives. Move to perpetual KYC. Get the ultimate beneficial owner right. Do it without adding headcount, without moving customer data anywhere, and be able to show the regulator exactly why every single decision was taken.”

Every one of those is the same problem wearing five faces: the unit does not have one customer. It has twelve records that no system agrees are the same person, and every control is applied to the copy in front of it rather than to the party itself.

Resolve the entity and the five problems change shape at once. Duplicate alerts collapse. Screening runs against the real party rather than a string. Ownership becomes traversable. Review becomes event-driven because the graph knows when something changed. And the answer to why stops living in somebody’s memory.

01

Fragmented data

The same customer exists a dozen times, reconciled by hand, never by the system. Controls apply to the copy, not the party.

02

Alert backlogs

Rules fire in isolation on unresolved records; investigators drown in volume, most of it the same customer arriving repeatedly.

03

Periodic review

A calendar-driven refresh cycle that is stale the day it completes, and blind to the change that actually mattered last Tuesday.

04

Opaque ownership

Chains that stop at the first offshore layer, with the gap recorded as a blank field rather than as a finding somebody must act on.

05

No lineage

When the regulator asks why, the answer is reconstructed months later from screenshots, spreadsheets and recollection.

The shape of it

Governed agencies, over one fabric.

Beneath, the Knowledge Fabric reads and resolves the estate in place. Above it, governed agencies reason, decide and act, with every output traceable to source — all wrapped in security, privacy and observability spanning every layer.

Fig. 00a  //  agencies reasoning over the fabric● every output traceable
DBsAPIsERP · HRSaaSWarehousesDocs · Streams The Knowledge Fabric unify in place · discover · schema & ontology · entity resolution no raw data leaves ONE RESOLVED KNOWLEDGE GRAPH The Agentic Layer rules & logic · agencies of agents · dialogue · agentic widgets governed · attributable Prioritised alertsInvestigated casesDefensible narratives
Fig. 00b  //  composite and generative reasoning on the fabric
SECURITY & PRIVACY — identity · role/attribute access · differential privacy · federated learning Sourcesany type Data Integrationsemantic detection Entity Resolutionattribute · active Knowledge Fabricresolved graph Composite + Gen AIexplainable Outputgrounded
Fig. 00c  //  security and observability span every layer
SECURITY OBSERVABILITY No-code Canvas Logic & Analytics The Knowledge Fabricresolved graph · governed · in place Sources Blockchain Cloud / On-Prem unified by a single development framework
Fig. 00d  //  when the regulator asks why◆ today the answer lives in someone’s memory
COREBanking PAYMENTSRails CRMCustomer SCREENINGVendor TRADEFinance DOCSContent ALERT BACKLOG

Perpetual KYC

The file is never finished.

Periodic review exists because nothing was watching. When the graph is live against source, review stops being a calendar event and becomes a consequence: a directorship changes, a sanction lands, an address moves, a payment pattern breaks — and the file reopens itself, at the risk tier that change deserves.

Fig. 01a  //  perpetual KYC — continuous, gated for material change● the file reopens itself
Changein graph Recomputerisk Gatematerial? Reviewonly if always on · noise-free
Fig. 01b  //  the gate — review only if material
transaction stream · in context Scenarios + scoringtypologies on the graph + counterparty risk+ ownership+ history Prioritised alertcontext-rich · ranked
What triggers

A change in the estate

New account, new counterparty, new document, new payment behaviour, a completed dispute, a closed product — any of it can move the risk position.

What triggers

A change in the world

A sanctions listing, a registry filing, an adverse-media item, a court record, an officer appointment — matched against what you already hold, not screened blind.

What follows

The work comes to you

The system stops being a place you go and becomes something that raises the case, with the evidence already assembled and the reason for raising it stated.

Screening

Screen the party, not the string.

A screening engine that compares text to a list will always trade false positives against missed matches, because it is solving the wrong problem. Resolution happens at the ontology level here: the fabric reasons over entities, not strings, so a name rendered in Arabic, Cyrillic, Han or Latin script resolves to one party — and one name never silently collapses two people.

Fig. 02a  //  screening — resolve, then match● the real party, not the string
Party resolved entity + aliases+ languages Matchfuzzy · scored Sanctions list PEP list Internal block Disposition+ rationale clear · escalate · case — all logged
Fig. 02b  //  disposition with rationale — clear, escalate, case
News Filings Registries Relevanceclassify · de-dupe noise dropped Entity linked to graph Risk signalattached · dated · sourced
Why the false-positive rate falls without lowering the bar

Most of the noise is not bad matching. It is the same customer arriving eleven times through eleven systems, each generating its own alert against its own copy. Collapse the copies into one governed record and a large share of the queue disappears before a threshold is ever touched — with the collapse itself recorded, scored and reversible.

Under the utilities

Lineage, joins and a graph that stays current.

Fig. 02a  //  every field carries its origin
SOURCE · scanning… PII · name acct no. key →join 12 sources 340 PII fields lineage ✓
Fig. 02b  //  twelve sources, 340 personal-data fields, lineage intact
ownsholds controlssendsscreened-by Customer Account Legal Entity Transaction Watchlist Counterparty derived from your data — not hand-modelled
Fig. 02c  //  new records extend the graph as they happen● always current
duplicates → CustomerAccountUBO TxnEntityCounterparty
Fig. 02d  //  the autonomy dial, L0 process-bounded to L4 fully agentic
YOUR SECURITY BOUNDARY · NO RAW DATA LEAVES Core banking Payments Customer / CRM Screening Warehouse active metadata → The Fabric resolved, in place

Ownership & control

Chains to natural persons — and an honest halt.

Traversal runs until it reaches natural persons or cannot proceed. Where it cannot, the halt is reported as a finding with the level reached, the percentage unresolved and the reason — not written into the file as a blank field that nobody is accountable for.

Fig. 03  //  layers resolved to the ultimate beneficial owner◆ the hidden common owner
Graph evidence Documents Timeline Dispositions Case fileassembled Narrativecited · defensible every claim linked to its source — survives an audit
Structure

Control, not just ownership

Shareholding, directorship, signatory rights, trusteeship and effective control carried as typed relationships, each with confidence, source and date on the edge.

Cross-source

The link written nowhere

A directorship in a filing plus a shareholding in a register plus a party already screened elsewhere in the estate. The conclusion exists only between them, and only a graph returns it.

Continuous

The chain is watched

A new filing, a transfer of shares or a change of officer reopens the traversal and re-scores the party — automatically, with the trigger recorded.

Alert triage

Clear the queue by resolving first.

Because the graph already knows what an entity is, rules express intent rather than brittle joins. “Funds in from a high-risk counterparty, out within twenty-four hours” is written against meaning. Change a threshold, replay history, see the effect — before it reaches production.

Fig. 04  //  from alert to filing, with a gate on every disposition● nothing dismissed silently
Alerts raisedrules, models and screening hitsResolved to entitythe twelve copies collapse to oneDUPLICATE ALERTS COLLAPSE WITH THE ENTITYAuto-dismissedwith a stated, auditable rationaleEACH DISMISSAL DEFENSIBLE, NOT SILENTEnriched & triagedgraph context attached before a human looksTHE ANALYST OPENS A PREPARED FILEInvestigatedevidence assembled across the graphNETWORK, TIMELINE, MONEY FLOWFilednarrative drafted, linked to sourceA PERSON APPROVES AT THE GATETHE BACKLOG IS NOT CLEARED BY LOWERING THE BAR. IT IS CLEARED BY RESOLVING THE ENTITY FIRST.HUMAN GATE ON EVERY FILING · EVERY DISPOSITION LOGGED WITH ITS BASIS · REPLAYABLE UNDER THE RULES IN FORCE AT THE TIME
Rule workHow it behaves hereWhat that buys the unit
AuthoringExpressed over resolved entities and typed relationshipsA typology survives a source-system change
VersioningEvery rule pinned, dated and immutable once usedYou can say which rule produced which decision
Back-testingReplayed against historical state, not today’sTuning evidenced before a threshold moves
DismissalRequires a stated rationale, recorded against the entityNo silent closure to defend two years later
EscalationRouted with the graph context already attachedThe analyst opens a prepared file, not a blank one

The workforce

Six agencies, each with one job.

An agency is a coordinated team of agents serving one purpose. Each runs at the autonomy its risk allows, from quietly assisting an analyst to acting under policy — and every one of them is composed by your people in the Studio, not shipped as a black box.

Autonomy 4 / 5

Monitoring

Watches flows and networks for typology hits continuously, against the live graph rather than a nightly extract.

Autonomy 4 / 5

Screening

Resolves names and entities against watchlists, sanctions and adverse signals — the real party, in any script.

Autonomy 3 / 5

Triage

Ranks and dismisses noise with a stated, auditable rationale carried on the entity.

Autonomy 3 / 5

Investigation

Gathers evidence across the graph and assembles the case, with every element linked to source.

Autonomy 2 / 5

Narrative

Drafts the report grounded in cited evidence. The filing itself waits at a human gate.

Autonomy 3 / 5

Quality

Reviews, challenges and checks the work of the other agencies — a second line built into the first.

Fig. 05  //  the six agencies, and where the person sits◆ the gate blocks until approved
ONE AGENCY · ONE PURPOSE · MEMBERS ARE AGENTS, NOT PEOPLETHE AGENCYThe financial-crime unit: six agencies over one resolved graph.Screeningresolve, then matchAdverse mediathe story, on the right entityPerpetual KYCrecomputed on changeTransaction monitoringscenarios with the graph in scopeOwnership & networkwalked to natural personsCase & narrativeassembled, not huntedAGENCY6 agentsWHERE THE PERSON SITSExecution pauses at the gate. It does not continue until a person approves.01PrepareThe agency gathers, resolves and reasons.Evidence assembled, not asserted.02Disposition or escalationHeld at the gate. The proposal, the basisfor it, and the approver are recorded.03ActOnly after approval. Signed, isolated,and written to the audit trail.AUTONOMY IS SET PER STEP, NOT PER AGENCY · SEE THE INTERACTIVE DIAL ON THE PLATFORM PAGE

Investigation

The investigator just asks.

The whole platform meets the analyst as conversation. Ask in plain language; the agencies query the graph, act, and answer with cited evidence — rendering live widgets the analyst can drive rather than a paragraph they have to verify by hand.

Nothing in that exchange is unsourced. Every claim carries the record it rests on, every merge is reversible, and every consequential step waits on the analyst’s authority.

DataFab — investigation console · case CR-4471grounded · cited · logged
Analyst

Why was customer C-4471 flagged, and who are they connected to?

Investigation agency

C-4471 triggered rapid pass-through: €1.2M received from a high-risk counterparty and moved out within 18 hours across three accounts. Two counterparties resolve to a single beneficial owner already on a watchlist. grounded in: transaction ledger · ownership graph · watchlist — view lineage

Analyst

Was this customer reviewed in the last cycle?

Investigation agency

Yes — reviewed and cleared. The ownership link post-dates that review by nine days and was never surfaced, because the review was calendar-driven. It is now attached to the file with the filing that missed it. reopened by: registry filing · confidence 0.91 · three sources merged

Analyst

Draft the narrative.

Narrative agency

Drafted, with every statement linked to the record it rests on. Held at the gate for your approval. human gate · awaiting analyst authority · the gate itself is logged

Illustrative exchange showing the utility’s behaviour. Figures are example values, not measured results.

The financial-crime utilities

Every function is a utility on the Fabric.

The unit does not buy another point tool. Each financial-crime capability is delivered as a utility — composed from platform building blocks, run by an agency, over the one resolved graph. Turn them on; they share the same entities, the same lineage and the same governance.

Platform utilities — the building blocks every utility is composed from

Entity managementList managementSource managementDocument managementAlert managementCase managementOrchestrationGraph analysisPolicy enforcementAccess managementKnowledge & Agentic StudioReporting engineMCP StudioVision-language-action
01Watchlist & sanctions screening

Screen the resolved entity — not the raw string. Because the customer is already one resolved entity in the graph, screening matches a real party against lists, with aliases, languages and prior dispositions in view. Fewer duplicate hits, every decision explained.

Resolve, then match — names, aliases and identifiers reconciled before the list lookup. Disposition with rationale — hits cleared or escalated with a stated, auditable reason. Carry the decision forward — yesterday’s clearance informs today, so the same alias is never re-litigated.

Composed of

List managementEntity managementAlert managementCase managementPolicy enforcement

Run by the Screening agency · autonomy: clear the obvious, escalate the rest.

02Adverse media screening

The right story, on the right entity. DataFab ingests open and licensed sources, judges relevance, and attaches negative signals to the resolved entity — not to a name that might be three different people. Each signal is dated and traceable to its source.

Composed of

Source managementDocument managementGraph analysisEntity managementAlert management

Run by the Adverse-media agency · grounded in cited articles, not generated summaries.

03Perpetual KYC

Customer risk that never goes stale. Periodic review becomes continuous. When the graph changes — a new counterparty, an ownership shift, a fresh signal — the customer’s risk is recomputed and, only if it matters, a review is raised.

Event-driven, not calendar-driven: reviews triggered by real change rather than an arbitrary cycle. Whole-customer view: risk judged across every account and relationship at once. Policy as configuration: the risk model and thresholds are owned by the unit, versioned and explainable.

Composed of

Entity managementSource managementOrchestrationPolicy enforcementAlert management

Run by the Monitoring agency · continuous, gated for material change.

04Transaction monitoring

Monitoring that knows who is involved. Scenarios run over money movement with the graph in scope — counterparty risk, ownership and history all in the same evaluation. The result is fewer, richer alerts that arrive ready to investigate.

Composed of

Graph analysisOrchestrationEntity managementAlert managementCase management

Run by the Monitoring agency · scenarios versioned, replayable against history.

05Ownership & network

See who is really behind it. Layered corporate structures become a traversable network. DataFab resolves entities across registries and internal records to surface the beneficial owner — and the hidden links between parties that look unrelated.

Pierce the structure: walk ownership chains to the ultimate beneficial owner. Find the hidden link: shared owners, addresses and counterparties across cases.

Composed of

Entity managementGraph analysisDocument managementKnowledge & Agentic Studio

Run by the Investigation agency · every link evidenced to source.

06Case & regulatory reporting

From evidence to filed report, in one place. The case assembles itself from the graph: evidence, documents, timeline and prior dispositions in a single file. The narrative is drafted with every claim linked to its source, ready for review and filing.

Composed of

Case managementDocument managementReporting engineOrchestration

Run by the Investigation and Narrative agencies · grounded, not generative.

The utilities, drawn

Each one composed from the same blocks.

Fig. 06  //  the six agencies, and where the person sits
ONE AGENCY · ONE PURPOSE · MEMBERS ARE AGENTS, NOT PEOPLETHE AGENCYEach composed from the same platform building blocks.Screeningresolve, then matchAdverse mediathe story, on the right entityPerpetual KYCrecomputed on changeTransaction monitoringscenarios with the graph in scopeOwnership & networkwalked to natural personsCase & narrativeassembled, not huntedAGENCY6 agentsWHERE THE PERSON SITSExecution pauses at the gate. It does not continue until a person approves.01PrepareThe agency gathers, resolves and reasons.Evidence assembled, not asserted.02Disposition or escalationHeld at the gate. The proposal, the basisfor it, and the approver are recorded.03ActOnly after approval. Signed, isolated,and written to the audit trail.AUTONOMY IS SET PER STEP, NOT PER AGENCY · SEE THE INTERACTIVE DIAL ON THE PLATFORM PAGE
Fig. 07  //  screening — resolve, then match
Party resolved entity + aliases+ languages Matchfuzzy · scored Sanctions list PEP list Internal block Disposition+ rationale clear · escalate · case — all logged
Fig. 08  //  disposition with rationale — clear, escalate, case
News Filings Registries Relevanceclassify · de-dupe noise dropped Entity linked to graph Risk signalattached · dated · sourced
Fig. 09  //  perpetual KYC — continuous, gated for material change
Changein graph Recomputerisk Gatematerial? Reviewonly if always on · noise-free
Fig. 10  //  the gate — review only if material
transaction stream · in context Scenarios + scoringtypologies on the graph + counterparty risk+ ownership+ history Prioritised alertcontext-rich · ranked
Fig. 11  //  layers resolved to the ultimate beneficial owner◆ the hidden common owner
Graph evidence Documents Timeline Dispositions Case fileassembled Narrativecited · defensible every claim linked to its source — survives an audit
Fig. 12  //  rules, risk scoring and processes — configured, versioned, explainable
Typologiesknown patterns Scenariosgraph queries Risk scoringweighted, tunable Orchestrationprocesses Caseprioritised every block configurable · versioned · explainable — no black-box scoring

The engagement

Not a software install. A transformation.

DataFab is delivered as a partnered programme: prove value on one utility, build the Fabric, compose the logic, stand up the agencies, then run it with you. Each phase is wrapped by a DataFab service — from consulting through to compliance as a service.

00
consulting

Mobilise & prove value

Data-strategy workshop, needs assessment, target operating model, and a proof of value on one utility — typically screening. Output: roadmap and a working proof of value.

01
delivery

Connect & unify

Connect sources in place, with no raw data leaving; data-quality assurance across the estate. Output: live connections and a quality baseline.

02
delivery

Build the Fabric

Discovery, schema and ontology generation, the dynamic knowledge graph and entity resolution. Output: a resolved graph and a derived ontology.

03
knowledge

Compose the logic

Domain expertise, business-rule development, reference scenarios and risk scoring built with your specialists. Output: typologies, scenarios and scoring.

04
delivery

Build the agencies

Configure agencies and agents, set autonomy, wire the dialogue and agentic widgets, train the unit. Output: live agencies and the investigator console.

05
delivery

Assure & go live

Validation and replay testing, governance sign-off, rollout support and comprehensive user training. Output: signed off, in production.

DataFab leads

  • The platform, the Fabric build and entity resolution
  • Agency configuration, autonomy and the dialogue layer
  • Governance scaffolding, lineage and audit by construction
  • Run, monitoring and compliance as a service

The unit provides

  • Access to sources within the boundary
  • Domain expertise — typologies, rules and risk appetite
  • Disposition standards and sign-off authority
  • The investigators who drive the agencies day to day

Durations are illustrative model output, not contracted. Phases overlap and compress with scope and data readiness.

Fig. 13  //  each phase wrapped by a DataFab service● consulting through to compliance as a service
wk 010203040+ 0 · Mobilise & POV 1 · Connect & unify 2 · Build the Fabric 3 · Compose logic 4 · Build agencies 5 · Assure & go-live 6 · Run & comply → value proven on 1 utility SERVICES · CONSULTING → DELIVERY → KNOWLEDGE → SUPPORT → COMPLIANCE-AS-A-SERVICE

What the unit gets

Less noise. Faster cases. A defensible record.

↓ down

Alert volume

Fewer, better alerts, raised on resolved entities rather than on twelve copies of the same customer.

↓ down

Investigation time

Evidence assembled rather than hunted — the analyst opens a prepared file.

↓ down

False positives

Context rather than isolated rule hits, so the threshold does not have to move to clear the queue.

↑ up

Analyst capacity

The agencies do the gathering; the analyst spends judgement rather than hours.

✓ assured

Defensibility

Lineage on every decision, produced as the work happens rather than reconstructed later.

Structural

One picture of the customer

Resolved across every system, so risk is judged on the whole rather than on the fragment in front of you.

Structural

Alert to narrative in one place

Detection, investigation and reporting on the same graph, not three tools and a copy-paste between them.

Structural

Change without rebuild

New sources, new typologies and new rules extend the Fabric. Nothing is re-modelled from scratch.

Directional outcomes shown for illustration — model output, not contracted. Magnitudes depend on the unit’s data and configuration.

Trust & governance

In financial crime, an answer is only useful if it survives a regulator.

DataFab is built so that the right answer and its justification are the same artefact.

01

Grounded

Every answer traces to the resolved graph and its sources — grounded, not generative.

02

Attributable

Each claim carries its lineage — attributable and defensible, not guessed.

03

Reproducible

The same question yields the same, replayable result — it survives an audit.

Governance that ships with the platform

Twelve compliance agencies are available out of the box — governance that ships with the platform, not a project bolted on after.

Defensibility

The answer to why is an artefact, not a memory.

Supervisors do not primarily ask whether the system found the right thing. They ask whether you can show how it decided, under which rules, on which data state, with whose authority — and whether the same inputs would produce the same result today.

Fig. 06  //  what crosses the boundary, and the in-boundary path◆ the gate
SOURCE DOCUMENTS — SOURCE OF RECORD, NEVER MIGRATED Customer agreements · broker correspondence · commission statements · signed forms · scanned records PDF · DOCX · JPG / PNG / TIFF · multi-page · degraded scans · handwritten annotation READ ON REQUEST FABRIC SERVICE · DOCUMENT EXTRACTION TRANSIENT — NO RETAINED CORPUS Classification gate Resolved from metadata BEFORE dispatch — never by inspecting content Then: machine-readable or OCR · cost · latency CLEARED BACKENDS On-premise GPU inference Only path for sensitive documents · no bytes leave self-hosted vision model External OCR service receives a transient copy · boundary crossed complex layouts · handwriting · forms Library extraction · traditional OCR machine-readable path · in boundary tried first where a text layer exists TRANSIENT COPY LEAVES THE BOUNDARY — GATE-CLEARED DOCUMENTS ONLY Returned: structured Markdown Headers, tables, lists and emphasis preserved — returned to the caller Returned with it: provenance Method · backend · classification basis · confidence · checksum · timestamp NOW READABLE BY Knowledge Fabric — entities resolved in place The document becomes one more source the graph can resolve Governance ontology — ethical walls, permissions, lineage and immutable audit NO DATAFAB DOCUMENT STORE · NO SECONDARY CORPUS
Model risk

Bounded by construction

Extraction and derivation are constrained by seed schemas. The system cannot invent entities outside them, and low confidence flags rather than fabricates.

Reproducibility

Replay, years later

The data state, rule versions and execution path that produced a result — not an approximation reassembled from logs.

Segregation

Ethical walls hold

Role- and attribute-based access at the graph, with compartments enforced across the connected environment. One fabric never means one undivided view.

Record

Tamper-evident

Hash-chained and encrypted, auditor role only, no delete capability. Produced as the work happens.

The compliance stack

Twelve domain capabilities on one federated graph.

Two layers of domain capability sharing the same entities, the same lineage and the same governance — rather than twelve products each with its own customer master, its own permissions model and its own audit story to reconcile. The technologies beneath them are platform capability, documented on the platform pages.

Layer 01 — business utilities

ScreeningCustomer due diligenceAdverse mediaClient lifecycle managementFraudFinancial intelligence

Layer 02 — enterprise utilities

Case managementAlert managementRules managementDocument managementSource managementList management
Source systemWhat the fabric readsWhat stays put
Core bankingCustomer, account and product structureEvery record
Payments & ledgerCounterparty, flow and pattern metadataEvery transaction
CRM & onboardingRelationships, contacts, onboarding stateEvery record
Screening & case toolsAlerts, dispositions, case stateEvery case file
Trade financeInstruments, parties, documentary stateEvery record
Document storesExtracted text on request, with provenanceThe source of record
Registries & listsGoverned enrichment, per-source isolatedHeld at the provider

Read-only, with your credentials, over the connection pattern your network allows. No ingestion, no secondary corpus, no customer data leaving the boundary.

Getting started

The first ninety days.

Deliberately small, and deliberately the part that hurts. One population, a handful of critical sources, and a governed agency running inside your boundary with the evidence produced as it works.

01
week 1

Plane and sources

A data plane stands up in your environment in hours. The first read-only connections are typically same-day; discovery begins cataloguing and profiling immediately.

02
weeks 2–4

Resolution on one population

Entity resolution runs at thresholds you set across a chosen book. Uncertain matches route to your people. The duplicate count becomes visible for the first time.

03
weeks 4–6

Semantic layer approved

The derived model is reviewed, corrected and approved by the people who own the domain — from evidence rather than a blank page.

04
weeks 6–10

First agency live

Triage or screening, composed by your team in the Studio, tested in a sandbox and published scoped and gated. Dispositions start carrying their rationale.

05
weeks 10–13

Assurance and replay

Enforcement points demonstrated against the engineering evidence pack; the audit and lineage stream proven end to end into your own security tooling; a historical case replayed under the rules in force at the time.

0 BCustomer data leaving your boundary
Read-onlyConnection posture to every source system
Per stepAutonomy set by risk, not one setting for the unit
Every oneDisposition carries a stated, replayable basis

Next step

Bring one book and the systems behind it.

The fastest way to test this is the population you already know is duplicated, across the systems nobody wants to migrate. Resolution makes the scale of the problem visible in weeks.