Six tiers, one deployment — the same system whether it runs in the cloud or inside the agency's own rack. Click a tier to open it.
What runs hereEvery stakeholder in the D2D picture meets the platform through one of these four — the same record, rendered for the job in front of them.
Why it mattersFour front ends, one backend contract. A new front end is a client, never a fork of the system.
What runs hereNothing reaches a service directly. Every call is authenticated, rate-limited and logged at the door before it is routed.
Why it mattersOne place to audit who asked for what — and one place to close if a deployment has to be sealed.
What runs hereThe layers of D2D are these services: classification, workflow, analytics and report generation each run as their own deployable.
Why it mattersA model can be retrained and re-deployed behind the same endpoint without touching the application above it.
What runs hereOne record, written once and referenced everywhere: evidence in object storage, its index in the database, its live state in the cache.
Why it mattersEvery element here has a self-hostable equivalent — which is what lets the same platform run inside an agency's boundary.
What runs hereThis is what the rest of the stack exists to serve: the models that turn a capture into a classified, defensible record.
Why it mattersSelf-hosted by design. No field record has to leave the agency's boundary to be understood.
What runs hereEverything above is portable: same containers, same services, cloud or on-premise.
Why it mattersSovereignty is a deployment decision here, not a rewrite.
The platform an agency buys, the engine that runs it, and the record of what it has done — each one a zoom level on the one before.
Five layers, one field record, capture to decision — all inside the agency's boundary. Click a layer to open it.
What reaches hereA director asks a question in plain language and gets an answer that traces, unbroken, back to one officer's capture in the field — without the data ever leaving the agency's premises.
What happens hereThe domain model reasons over the whole platform in the agency's own vocabulary — and when it reports on a record, it cites the original capture rather than paraphrasing it.
Hands upwardConsolidated decision insight — the whole platform reduced to one interface.
What happens hereA record stops being one record and joins the population: mapped, analysed against trend and hotspot, quality-checked, then converted into a response — a case, an inspection, a directive.
Hands upwardEnforcement inputs · data visualisation · analytics & reporting · domain health analytics.
What happens hereThe record lands in the single database, is classified and verified against the agency's own past records, and enters the workflow that will chase it to closure — with its report already generated.
Hands upwardTraceability in every report, and submission without anyone re-keying it.
What happens hereA field officer captures an observation on site. Before it is saved it is stamped with where, when, who, what and how — provenance applied at capture, not reconstructed afterwards.
Hands upwardSystematically recorded, digitised field reality — the input every other layer depends on.
The platform's middle layers as one run. Nothing crosses the dashed boundary outward. Press a chapter to keep only its path.
We teach, it learns. Signal is captured where it happens, computed on hardware inside your fence line, returned as decisions — the data comes from you and belongs to you.
Next view Every chapter the core is put to work on becomes dots on the ball. Pick one above to see how much sits behind it. Constellation →
Eight hubs, one dot per thing the core has produced, each tied to the chapters it belongs to — live from neuon.ai, so it is the same list the site itself shows. Press “Watch it grow” to run it from the start, or drag the year yourself.