The flagship difference

Your next ten clients are already in your data.

Every invoice, contract and KYC file you process adds companies and relationships to a private knowledge graph — a live map of the trade network around your book. It is an origination engine, not a visualisation.

Watch

How the knowledge graph powers a trade finance business

Two minutes: the graph building itself from your own document flow, and the playbooks that turn it into origination and risk insight.

2:16 · with narration

How it works

The graph builds itself

No data-entry project, no integration programme. The graph is a by-product of running your book on SQF.

1
A document arrives
An invoice names a counterparty you've never met. SQF creates the record automatically — issuer, debtor, amounts, terms.
2
An AI analyst screens it
A compliance check and a credit report run the moment the company appears. A human analyst confirms the finding — nothing enters your network unvetted.
3
The graph learns
The company joins the map with its role — supplier, buyer, client — its directors and shareholders from agency KYC files, and every relationship it touches.

You do the lending. The graph does the remembering.

The flywheel compounds: more flow builds a richer graph, a richer graph surfaces more origination, and every new client brings their own trading network with them.

What it looks like

A corner of a real trade graph

Companies with their roles, supply relationships with volumes and terms, and people from KYC files connecting borrowers no flat client list would ever link. The names below are illustrative — the shapes are exactly what the graph stores.

Opportunity playbooks

Four ways funders turn the graph into business

Worked examples, drawn from how the platform is used. Each one is a single query against your own data — not a data-science project.

Anchor-led supplier finance

Your client Meridian Foods buys from 14 suppliers you've already seen on invoices. Nine aren't your clients yet — but they're KYC-screened, and their volumes and payment terms are on record: the top three invoice RM 4.2M, RM 2.9M and RM 1.7M a year at 60-day terms. One query returns the list, ranked. That's an anchor-approved early-payment programme with nine pre-qualified prospects — sourced from your own flow.

Query: suppliers of a named client, ranked by 12-month invoice volume, excluding existing clients.

The factoring cross-sell you already underwrote

A supplier invoices three separate buyers in your network — you fund only one of those relationships. The graph shows their whole receivables position across your book: RM 6.1M a year at 75-day average terms, with payment behaviour you've already observed. An invoice-finance conversation where the underwriting evidence exists before the first meeting.

Query: counterparties supplying more than one company in the network, with volume and terms per relationship.

Related-party exposure — before the committee, not after the default

Two borrowers with no visible connection. The graph knows the same person is a director of one and a 55% shareholder of the other — and that both are supplied by a third company he holds an interest in. Three hops, one query. Concentration you can price, instead of discover.

Built from agency KYC files: director-of, shareholder-of and has-interest-in relationships, filtered to current officers only.

The growth signal that opens the term-loan conversation

A client's invoice throughput grows 40% across two quarters while facility utilisation holds above 90%. The graph and the ledger flag the working-capital gap together — your relationship manager opens the term-loan conversation before the client starts shopping for one.

Signal: invoice volume trend from the graph, joined to facility utilisation from the credit-limit register.

Plain language

Ask the network a question.

Saved opportunity queries come out of the box — anchor programmes, factoring candidates, growth signals. For everything else, ask in plain language: the question is compiled into a graph query, and the answer comes back with its evidence trail.

You ask —

“Which companies in my network supply more than one of my clients?”

The graph answers —

7 companies · ranked by connection count · each with the invoices, contracts and KYC findings behind the answer

For investors

Capital deployed against a visible, screened trade network — not an abstract book. The same graph that finds opportunities shows a funding pool exactly what its capital finances. How funding pools work.

What it’s built on

A dedicated graph database per funder, projected in real time from the platform’s event backbone. Personal identifiers used for entity resolution are never exposed through any interface.

Bring one month of your invoice flow — we'll show you the network inside it.

A working session on your own data, not a canned demo.

Book a working session