IntroducingUK · EU

The complete data foundation your AI was waiting for.

A managed catalogue, a typed ontology, a context graph, conversational analytics and an agent layer. One product. Six weeks. Branded as yours, deployed in your tenant. Built for industries the regulator is asking questions of.

Book a walkthrough →See it answer a question
Time to deploySix weeks
What’s includedCatalogue, graph and agent layer
Runs inYour tenant, your keys
Built forRegulated industries
01 / The problem

Your AI investments have not landed because the data foundation underneath was never built for AI to read.

80%
of generative AI pilots show no measurable EBIT impact. McKinsey, State of AI 2025.
70%
of high-performing organisations still struggle with their data foundations. BCG, Build for the Future.
5%
of organisations have reached future-built data maturity. Wavestone, Data and AI Leadership Exchange 2025.

“We have a data lake, three different catalogues and four failed copilot pilots. The agents cannot tell which version of the truth to use.”Chief Data Officer, FTSE 250 insurer

02 / What we deliver

One product. Five layers. Everything your AI needs, in one engagement.

/ 01

A managed data catalogue

We deploy a complete catalogue layer in your tenant. It crawls every source system, profiles every column, classifies every field, tracks lineage and indexes the lot. Branded as yours, run by us.

Catalogue
/ 02

A typed ontology

Your catalogue gets bound to a canonical ontology for your industry. Two to four hundred typed entities and the relationships between them. The semantic layer your AI needs to actually reason.

Ontology
/ 03

A live context graph

Materialised, queryable, walkable, citable. Every node and edge carries provenance back to source. The graph compounds with every customer interaction.

Graph
/ 04

Conversational analytics

Your team types questions and gets charts grounded in the graph. Drill from any chart point to the underlying entities and the citation trace. Export to PowerPoint or Excel.

Analytics
/ 05

An agent layer

A retrieval API your existing copilots embed. Every answer returned with the reasoning trace, the citations and the audit log. The artefact a regulator will actually accept.

Agents
/ See it work

Pharma. Water utilities. Public sector building safety. Same foundation, every answer traced to source.

An answer the regulator actually accepts.

Pharma reg affairs · Water utilities · Building safety · Insurance claims

Drop in a CSV. Watch the platform build the ontology, populate the graph, then answer a question with the citation trace and reasoning steps next to the chart.

Open the live demo →Walk through with us
03 / Vertical packs

The whole foundation, configured for your industry. Six weeks to production.

A vertical pack is the entire platform pre-configured for one industry. Catalogue connectors mapped to the systems you actually run. Ontology pre-built around the entities your regulator cares about. Analytics out of the box. The pack is what we deploy. The platform is what runs underneath.

Live · 2026

Pharma regulatory affairs

~400 entities · trials, indications, dossiers, signals

Catalogue connectors to Veeva Vault, Argus Safety, Master Control. Pre-built submission timeline analytics, signal trend dashboards, regulatory commitment tracking. Aligned to EMA, FDA and MHRA artefacts.

Veeva VaultArgus SafetyMaster ControlEUDAMED
Live · 2026

Water utilities

~320 entities · assets, catchments, permits, capex

Catalogue connectors to Maximo, AssetWise, EDM telemetry, GIS. PR24 outcome reporting, AMP8 capex tracking, EA spill compliance and Cunliffe-aligned governance evidence served from one foundation.

IBM MaximoBentley AssetWiseEDM telemetryEA returns
Live · 2026

Building safety and social housing

~250 entities · buildings, dwellings, defects, residents

Golden-thread compliance under the Building Safety Act. Awaab’s Law reporting on damp and mould. The accountable-person artefact the regulator is going to ask for.

CivicaNECAareonBuilding Safety Regulator
Next · Q3 2026

Insurance claims and underwriting

~350 entities · policies, perils, reserves, treaties

Catalogue connectors to Guidewire, Duck Creek, ECF. Reserve adequacy, peril concentration and Solvency II ORSA evidence served from one foundation.

GuidewireDuck CreekECF / A&S
On the roadmap

Medical device and post-market surveillance

~300 entities · devices, indications, FSNs, recalls

EU MDR, IVDR and FDA UDI compliance as a queryable graph. Periodic safety update reports drafted from live data, not retrieved from a folder.

On the roadmap

Financial crime and AML

~280 entities · counterparties, transactions, typologies

Beneficial ownership networks, transaction patterns and FATF typology matching as a graph. The MLRO artefact the regulator wants to see.

/ Architecture

One foundation. Five layers. Continuous flow up. Citable answers down.

live · continuous flow|SOC 2 · ISO 27001 · GDPR · GxPCrawling sources
YOUR TENANT · YOUR VPC · YOUR ENCRYPTION KEYSSOC 2 · ISO 27001 · GDPR · GxPCONSULTANCY PARTNERDeploys, configures, supports. Owns services revenue. We own the platform.CO-SELL · 6-WEEK PLAYBOOKMulti-customer admin · pre-built demosUSERS AND SYSTEMSDomain analystasks the regulator-grade questionCustomer copilotgrounds every answer it givesCompliance officeraudits, exports for regulatorExecutivereads the dashboard, signs offRegulatorarrives with questionsLAYER 05 · CONSUMPTION SURFACES · WE DELIVERSame graph, four ways. Humans ask. Agents call. Compliance audits. Executives report.Citable answerUI · API · MCP serverConversational analyticsdrill from chart to entityAgent grounding APIyour copilots embed itAudit and lineage explorerregulator-grade trace · exportableLAYER 04 · VERTICAL ONTOLOGY PACK · WE DELIVERThe whole foundation, pre-configured for your industry. Six weeks to production.Pharma reg affairsLIVEWater utilitiesLIVEBuilding safetyLIVEInsurance claimsQ3 2026+ your verticalLAYER 03 · SEMANTIC LAYER · WE DELIVERBinds catalogue metadata to typed entities. Builds the context graph your AI can reason against.ONTOLOGY BINDINGraw fields to typed entitiesCONTEXT GRAPHqueryable, walkable, citablePROVENANCEVERSIONEDhistorical answers reproducibleRBAC ON GRAPHpredicate-level access controlREGULATOR-READYLAYER 02 · MANAGED CATALOGUE · WE DELIVER[branded as yours]A complete catalogue layer in your tenant. Crawls, classifies, profiles and indexes. Always on.CRAWLS YOUR SOURCESMETADATA INGESTIONSEARCHABLE INDEXSnowflakeDatabricksVeeva VaultArgus SafetyGuidewireSAP+ 70 source connectorsschema scancolumn profilelineage tracePII classificationglossary mappingfreshness checkMETADATA INDEXtables · columns · fields · keysdocuments · dashboards · modelsowners · stewards · domainstags · glossary · classifications12.4M assets847 dashboards186 owners2341 tagsLAYER 01 · YOUR DATA SOURCES · YOUR ENVIRONMENTSnowflake, Databricks, Veeva, Guidewire, SAP, Salesforce and the long tail. We connect, we never migrate.FEEDBACK · CORRECTIONS · LEARNING
SubstrateLayer 02 is powered by open-source DataHub, the catalogue trusted by LinkedIn, Pinterest and Coinbase. We deploy and manage it inside your tenant, branded as part of your foundation. Honest about the substrate, opinionated about everything we build on top.

We connect to the data you already have. We call the model you already trust. We run in the tenant you already control.

Connects to your data sources
SnowflakeDatabricksBigQueryPostgresSalesforceSAPVeeva VaultGuidewire+ 70 more
Calls the model of your choice
ClaudeGPTGeminiMistralOpen weightsBring your own
04 / Why us

The questions a CDO asks us in the first meeting. And how we answer them.

vs. Palantir Foundry

“Why not just deploy Foundry?”

Six weeks not six months. Pre-built vertical packs instead of bespoke design. A tenth of the implementation cost. The whole foundation comes from one engagement, not a multi-year programme.

vs. Vector RAG

“We already have a copilot on a vector store.”

Citable answers, not plausible ones. Multi-hop reasoning across typed entities. Every claim traces to a graph path your QA reviewer can audit. The regulator gets evidence, not embeddings.

vs. Atlan or Collibra

“A catalogue is just half the answer.”

Catalogues describe data. We make it agent-readable. A catalogue is one of five layers we deliver. The graph, the analytics and the agent layer are why your AI actually works.

Tell us where your AI got stuck. We will tell you whether the foundation is the reason.

A 30-minute call with someone who has done this before. No deck, no demo theatre. Bring your hardest stuck pilot.

Book a walkthrough →Read the EU AI Act guide