The provenance network · the platform

One object in. A scored answer out.

A painting. A watch. A piece of heritage. One goes in the front door; a scored, sourced answer comes back. This is the machine that does it — pick a workflow and watch it run.

Is it real? Worth what? What’s its story? The same machine answers all three.

The platform in five blocks Target architecture · live today marked
1 · Pick a workflow
2 · The path lights up as your object moves through the platform.
Client
veradis platform · your data, in your region
Network & consumers
Client
Web & mobile app
Institution system
Sign-in
Front door
Identity & access
API gateway
Application API
Job orchestrator
Queue
Processing engines
Ingestion Engine
Enrichment Engine
Inference Engine
Verification & score
Read / write
Data & storage
Your object store
Platform database
Knowledge graph
Vector store
Reference corpuscompounding
Audit ledger
Score
Output & network
Scored report → you
Verify API → consumers
Enrich-and-Return → system
Model serving vision · OCR · handwriting · embeddings · Claude (narrative) shared layer
Governance & audit rails curator sign-off · audit ledger · data residency & consent across everything
The learning loop — every verified answer flows back into the Reference corpus, so the next query is stronger.
Verify an object

    Processing engine
    Data store
    Reference corpus — what compounds over time
    Output / network
    Your own system
    The five engines

    Five engines. Each does one job.

    The engines are where the work happens. Four do the work; a fifth — governance — keeps them honest. The tools run inside them, and each engine’s colour here is the same colour that tags its tools on the Tools page.

    Ingestion

    It gathers

    Pulls the real records and reads your photos and papers into facts we can check.

    Enrichment

    It fills in

    Builds the object’s story — who made it, who owned it, where it has been.

    Inference

    It connects

    Finds the link to another collection that no one had spotted, and what it’s worth.

    Verification

    It scores

    Weighs the evidence and returns a confidence score — or says the evidence runs out.

    Governance

    It keeps it honest

    A person signs off, every step is logged, your data stays in your region and yours.

    The learning loop — every answer grows the reference corpus, so the next one is sharper.
    Where we are today

    This is the target architecture — where the platform is going. Working in the demo today: verifying and appraising an object end-to-end, reading marks and documents, matching people and places, the cross-collection links, the confidence score, the evidence trail, and a curator’s sign-off — on five institutions and 20'000+ objects, not yet at production scale. The two workflows marked Next — syncing enrichments back to your own system, and a Verify API for others to query — are on the way. New tools slot in behind the same doors, so the shape doesn’t change as it fills in.

    One object in. Five engines. A scored answer out.

    Watch the machine run on a real object.

    Submit a photo and follow it through, live — every source named.

    See it live No account needed to look