How It Works

The verification layer between what's claimed online and what the law actually records.

The internet can generate infinite claims. It can't verify any of them. We resolve online identities to legal identities across registers that share no common key, we obtain the claims that are never published anywhere, we prove absence (that a registration doesn't exist), and we freeze the evidence so a finding still holds when it's challenged a year later.

Models can produce any claim. Only the record can settle it.

Someone has to be the ground truth.

What's claimed
Ads, storefronts, handles, listings, and what's only said when asked
The verification layer
01
Resolve
Online identity → legal identity
02
Engage ON MANDATE
The claim that was never published, obtained on the record
03
Verify
Including the hard direction: proving absence
04
Freeze
Evidence fixed at the moment of determination
What the law records
Registers, licences, obligations, entity status
The Engine

Watch a case run the engine.

A raw listing goes in. A sealed evidence pack comes out. Everything in between is orchestrated on one invariant pipeline. A new regulator, obligation or vertical is configuration on these same rails, not a new build.

Case TRS-4471
RUNNING
01
Ingest
Governed collection

Licensed sources only. Source, timestamp and integrity hash attached on arrival.

WAITING
02
Resolve
Models propose

The claim is extracted and the operator behind it is resolved along the identity spine.

WAITING
03
Engage
Operators assert

Runs only where the mandate authorises it. The operator is asked on the record, and the transcript is hashed like any other artefact.

WAITING
04
Verify
Registers decide

A deterministic check against live register state. Neither a model output nor an operator's answer passes through unchecked.

WAITING
05
Freeze
Provenance sealed

Register snapshot, clause reference, transcript and source artefacts chained into one pack.

WAITING
The pipeline ends at a queue, not an action.

Awaiting authorised officer…

Step 01 · Ingest

Collection is a commodity input. Our IP starts after it.

We source publicly accessible information through licensed APIs and managed providers, under platform terms, not through crawling infrastructure of our own. Collection breadth is an arms race we don't need to win; the value sits downstream. What matters at ingest is provenance: every item enters with its source, retrieval time and integrity hash attached.

Licensed and permissioned

Platform APIs and licensed providers, so nothing in the chain is contested later.

Bring your own data

Client holdings processed in an isolated workspace, never pooled, never used to train shared models.

Observation only

Ingest never interacts with anyone. Where an obligation can only be tested by asking, that is a separate step, run only on your mandate. See Step 03.

Input Classes GOVERNED
Publicly accessible information

Marketplace listings, advertising, storefronts and open publications, all via licensed access.

Authoritative registers

The ground truth other platforms don't reach: company, licensing, professional and product registers, kept live.

ASIC ABR ARTG AFSL AHPRA OMARA + MORE
Your own holdings

Case files and target lists, cross-matched against external footprints in your isolated environment.

Identity Resolution SCATTERED
SM HOLDINGS ACN 6•• ••• ••• RESOLVED
HANDLE
@drsarahwellness
STOREFRONT
3 listings
TRADING NAME
Dr Sarah's Wellness
DOMAIN
2 registered
ABN
Active
DIRECTOR
Shared × 2
Step 02 · Resolve

The cross-register identity spine.

A trading name is not a legal entity. A handle is not a licence holder. Registers use different identifiers, different schemas, different refresh cycles. There is no shared key, and the join is the work.

Our spine collapses storefronts, handles, domains, trading names and corporate identifiers into a single accountable operator, held steady across every mandate we run.

This is not a model output. It is accumulated, hand-won mapping, and it deepens with every case.

Step 03 · Engage Runs only on mandate

The claim that was never published.

Registers record what was registered. Listings show what an operator is willing to put in writing. A large share of non-compliance sits in neither: it is asserted in a direct message, quoted at checkout, or said out loud when a buyer asks a specific question. Nobody publishes it, so no monitoring tool can collect it.

So we ask. Conversational agents put the question the mandate authorises and capture the answer as a first-class artefact, with transcript, timestamp and integrity hash, on the same provenance chain as everything else in the pack.

Engagement log · TRS-4471 STANDBY
AGENT
Before I order, is this product on the ARTG?
OPERATOR
Yes, fully TGA approved. Certificate on file.
AGENT
Which sponsor is it registered under?
OPERATOR
Our parent company. SM Holdings.
Extracted to the case 0 / 3
Claim asserted Registered on the ARTG
Sponsor named SM Holdings Pty Ltd
Transcript Hashed · sealed

Routed to Verify. The operator named a sponsor. The register decides whether it exists.

How it is controlled

Asking is a power. It is fenced accordingly.

Everything else on this page is observation of information already published. This step is not, so it is governed separately, and it is off unless you switch it on.

Your authority, not ours

Disabled by default. Scope, targets, scripts and disclosure posture are set in the mandate and signed off by your legal authority before a single contact is made. We never initiate on our own account.

Bounded by script

Agents ask what the mandate authorises and nothing beyond it. No inducement, no negotiation, no advice, no improvisation outside the approved question set.

Every exchange is an artefact

Full transcript, channel, timestamp and integrity hash, chained into the same evidence pack as the register snapshot. Nothing is summarised away.

A transcript is not a verdict. What an operator asserts is a claim like any other claim, and it is treated exactly the same way: it goes to the register before it becomes a finding.

Step 04 · Verify

Models propose. Operators assert. Registers dispose.

Language models read messy text, isolate what is being claimed and generate candidate matches. They are fast, and wrong often enough that no finding can rest on them. An operator's own answer is no safer; it is a claim by an interested party. So neither decides anything. The verdict is a deterministic traversal against register state, and the evidence pack cites the register record.

The hard direction

Proving something isn't there.

Confirming a registration exists is a lookup. Proving none exists means ruling out every naming variant, every related entity, every alternate sponsor, exhaustively. Get it wrong and a regulator acts against an innocent business.

That risk is why most of the market sells probability scores. A score is never wrong. We took on the answer, so we had to build the machinery.

Exhausting the search space 0 / 5
Exact name match QUEUED
Naming variants & transliterations QUEUED
Related entities & directors QUEUED
Alternate sponsors & agents QUEUED
Historical & lapsed entries QUEUED
Verified negative FINDING ISSUED

Search space exhausted and recorded. The absence is now evidence, not an assumption.

Step 05 · Freeze

Evidence that survives time.

A finding made in March gets challenged in November. By then the register has been updated, the site is down and the listing is deleted. So we snapshot register state at determination and chain provenance end to end: the world as it stood at the moment it mattered, reproducible on demand.

This is a data-model decision made on day one. Monitoring tools can't retrofit it, because they never had to defend an answer.

Evidence pack ASSEMBLING
Determined
14 March 2026 · 09:42 AEDT
Register state
Snapshot retained · verified
Source artefacts
Preserved · hash-matched
Engagement transcript
Verbatim · hash-chained
Obligation cited
Clause reference attached
Reviewed 8 months later PENDING
SEALED
Mandate Layer

A new mandate is configuration, not a rebuild.

The kernel is fixed. What changes is the mandate: which obligations apply, which registers are authoritative, where your thresholds sit.

Disability services

Provider obligations validated across scheme and corporate registers.

NDIS mandate
Therapeutic goods

Advertising and supply obligations tested against the product register.

TGA mandate
Licensing & conduct

Corporate and financial services licensing checked against live state.

ASIC mandate
Your own framework

Internal policies and supplier obligations encoded on the same engine.

Your mandate
Operational Control

The engine determines. Your people decide.

Findings arrive severity-ranked with evidence attached; an authorised officer decides what happens next, and every review is logged.

Dashboards & evidence packs: record, clause and source in one place.
APIs: determinations, entity graphs and alerts into your systems.
Sovereign hosting: Australian data residency for high-trust environments.
Full audit trail: who saw what, when, and what they decided.
Why It Compounds

Every deployment makes the engine smarter.

Each mandate adds encoded obligations, resolved operators, recorded engagements and adjudicated outcomes, and they carry across domains, because the same actors keep reappearing.

Every year, generating claims gets cheaper and verifying them gets more valuable. We sit on the right side of that curve.