Artec Neo · by CITRIS Global

Your buildings already know what they need. Artec Neo is how they tell you.

Every asset. Every site. One intelligent platform — covering asset, risk, task, expenditure and compliance across FM, PFI/PPP, local authority and fleet estates.

AI proposes. Systems dispose. You decide.

Illustrative of the platform's own demo estate — not a customer figure.

An animated recreation of the Artec Neo cockpit. It surveys four assets and assigns condition grades from A to X, builds a five-year expenditure forecast, then the Asset Intelligence Engine writes a recommendation with a stated confidence score — for example, that an air handling unit in condition B with ten years of remaining life should stay on routine servicing with replacement reserved for 2036. The recommendation then waits for a human to approve or review it. No action is ever taken automatically.

The problem

  • 01

    Your register is a spreadsheet.

    Twenty years of column drift, three people who understand it, and no single answer to “what do we own?”

  • 02

    Your audit trail is an argument.

    When the dispute comes, “our records say” meets “our records say” — and the loudest consultant wins.

  • 03

    Your capital plan is a guess.

    Assets replaced on anniversaries rather than evidence, and a forecast nobody in finance actually believes.

None of this is a software problem. It is an evidence problem — and evidence is what the platform is built to produce.

The platform

Six reasons this is not another CAFM.

Each card demonstrates its own claim. Hover one, focus it with the keyboard, or just watch — the audit card verifies a real hash chain, the accessibility card cycles all three shipped themes.

  • One platform

    FM, PFI/PPP, Local Authority, Highways, Fleet, Real Estate — one register, one login.

    Multi-vertical from the data model up, not a CAFM with bolt-ons. A contractor running PFI schools and a council running highways use the same platform, each seeing only their own world.

    Four-level asset taxonomy: vertical → domain → group → type.

  • Asset Intelligence Engine

    Every asset gets an opinion.

    Per-asset recommendations with stated confidence — keep and service, plan replacement, act now — plus portfolio-wide triage that surfaces what needs attention today.

    The AI explains the score. It doesn’t invent it.

  • Provable history

    An audit trail that can prove itself.

    Not an audit log — a cryptographic hash chain. One click verifies the entire history has not been altered, and exports the proof.

    For PFI penalty disputes and regulator inquiries: “our records prove”, not “our records say”.

  • Accessibility

    Built to WCAG 2.2 AA — in all three themes. Including your brand.

    Light, dark and high contrast. Keyboard-complete, screen-reader tested. White-label branding that stays accessible: a tenant’s brand colour is derived per theme, so their identity never breaks legibility.

    Procurement asks for the conformance statement. We hand them one.

  • Security

    MFA on by default. Four-eyes approvals. Deny-by-default access.

    Not settings a customer must remember to enable — the shipped defaults. Row-level tenant isolation, or a dedicated database if your risk appetite demands it.

    Per-tenant AI spend caps, so intelligence never becomes an uncontrolled bill.

  • Onboarding

    Bring the spreadsheet you’re ashamed of.

    The intelligent importer reads messy registers — inconsistent columns, twenty years of drift — classifies the fields, proposes the mapping, and a human approves it.

    Data migration is the graveyard of CAFM implementations. We make it the first good day.

The business case

Your numbers, your assumptions — we just do the arithmetic.

We have no interest in inventing a case-study percentage for you. Move the sliders to your own reality and argue with the assumptions; every one of them is stated underneath the figure it produces.

Your estate

Everything you would need to inspect, maintain or replace.

Buildings, depots, campuses or network sections.

The share of spend that responds to failure rather than preventing it.

Deductions, abatements or performance penalties actually incurred.

Across everyone who touches a board pack, a return or a compliance report.

Hourly, including on-costs. Your assumption, not ours.

Consultant days quoted to get your register into a new system.

Indicative annual value, on your inputs

£0

Not a quote, not a guarantee, and not a customer result. An arithmetic model of your own figures under the assumptions listed below.

  • Penalty avoidance £0

    Assumes SLA tracking and triage catch one third of last year’s breaches before they cost.

  • Reactive → planned shift £0

    Assumes planned work costs materially less than emergency response, applied to a 10-point shift in your own ratio.

  • Reporting time returned £0

    Assumes 60% of manual compilation is replaced by scheduled and self-serve reporting.

  • Migration displacement £0

    Assumes the intelligent importer displaces half of the quoted consultant effort.

Capital confidence

The line we will not put a number on. Condition-based forecasting replaces anniversary-based replacement — you stop renewing assets with useful life left, and stop being surprised by the ones without. The five-year forecast fills in from evidence rather than from a spreadsheet nobody in finance believes.

Computed entirely in your browser. Nothing you enter here is transmitted, stored or logged.

On artificial intelligence

We built an AI copilot. Then we refused to ship it until it earned it.

NeO — our agentic asset copilot — is built, wired and deliberately held behind evaluation gates until it is proven against real client data. Because a copilot that invents plausible answers about your compliance obligations is not a feature. It is a liability.

When NeO answers, it cites its sources, shows its working, and operates inside per-tenant cost caps. Content safety runs on every message in both directions and fails closed. Personal data is tokenised before it reaches the model and restored only on the way back to the person who owns it. Every tool the model can reach is explicitly catalogued, tier-gated and permission-checked — and mutating tools stop and ask a human first.

The rule everything obeys

AI proposes. Deterministic systems dispose. You decide.

The intelligence you can use today — asset recommendations, portfolio triage, intelligent import — follows that rule without exception. Every recommendation is explainable. Every action needs approval. Every cost is capped. The scoring itself is deterministic: the AI explains the score, it doesn't invent it.

  • Grounded

    Answers are retrieved from a governed corpus — legislation, standards, and your own tenant data — and every claim carries a citation you can open.

  • Fail-closed

    Content safety and PII redaction treat their own outage as unsafe. If the classifier is down, the message does not go through.

  • Capped

    Per-tenant spend budgets with token, latency and cost logged per call. AI never becomes an uncontrolled line item.

  • Gated

    Tools the model may not use are hidden from it entirely — it cannot propose what it cannot see — and mutating tools require explicit confirmation.

CITRIS AI Engineering

We build agentic AI that works alongside what you already run.

Custom agents, frameworks and accelerators that sit beside your existing applications and databases — never a rip-and-replace.

Most organisations do not need another platform. They need their current systems to get smarter. We design and build agentic AI with the same engineering discipline that runs inside Artec Neo, connected to what you already own.

  • Ingest

    Data onboarding agents

    Point them at any legacy database, spreadsheet estate or API. Schema inferred, mappings proposed, humans approve, deterministic pipelines execute.

  • Extract

    Document-to-record extraction

    O&M manuals, contracts and certificates become structured, evidenced data — with per-field confidence and a citation back to the source page.

  • Decompose

    Obligation intelligence

    Contracts and SLAs decomposed into dated, owned, trackable obligations, so nothing lives only in a PDF nobody has opened since signature.

  • Query

    Ask-your-systems

    Natural-language answers over your own data, read-only by construction. The agent cannot write, so it cannot break anything.

  • Build

    Custom agent frameworks

    Designed around your workflows and deployed in your cloud — AWS Bedrock, Azure AI Foundry, or your own endpoints. Your data never leaves your boundary.

The trust frame — reused from the product, because it is the moat

  • Propose / dispose

    Agents draft. Deterministic code executes. Humans approve. The model is never the last thing between an idea and your database.

  • Your model, your keys, your cloud

    Bring your own model on AWS or Azure. We build to your boundary rather than asking you to move inside ours.

  • Evaluated, not vibes

    Every agent ships with a measured accuracy number against a held-out set, and a regression gate that fails the build when it drops.

  • Governed by default

    Audit trails, cost caps, tool allow-lists and PII redaction. The control plane is part of the build, not a phase-two extra.

Artec Neo is our proof of work. Every discipline we sell — evaluation gates, audit chains, human-in-the-loop, cost governance — runs in production inside our own platform first.

Industry verticals

One data model. Six worlds.

Verticals are configured, not forked. A tenant subscribes to the ones they operate in, and the asset taxonomy, risk columns, compliance duties and forecast rules follow automatically.

Facilities Management Statutory compliance, PPM, SLA performance and contractor scorecards on one register.
  • Compliance RAG with Black for overdue statutory duties
  • PPM scheduling across seven frequency types
  • Work orders with SLA response and fix windows
  • Criticality and BMS linkage per asset
PFI / PPP Lifecycle funds, payment mechanism, handback readiness and the evidence to defend it.
  • Concession modelling with RPI and discount rates
  • Lifecycle scenario comparison and fund depletion alerts
  • Handback assessment against contractual condition
  • Immutable decision records with approval chains
Local Authority Citizen reports, triage, statutory duties and CIPFA-shaped capital forecasting.
  • Unauthenticated citizen reporting with duplicate detection
  • Triage into asset linkage and work orders
  • Public-sector equality duty and FOI-aware records
  • Five, ten and fifteen-year forecasts with RPI adjustment
Highways UKPMS condition surveys, defect categorisation and Section 58 defence evidence.
  • SCANNER survey import: RCI, rutting, texture depth, cracking
  • Inspection and defect registers with category codes
  • Scheme planning by road hierarchy and treatment type
  • USRN-anchored site cross-cuts
Fleet MOT, insurance, walkaround checks, EV battery health and disposal timing.
  • VIN, mileage, MOT and insurance expiry tracking
  • Driver walkaround checks and damage events
  • EV charging sessions and battery health percentage
  • Total cost of ownership and disposal recommendation
Real Estate Occupancy, rent roll, service charge and dilapidations against the same asset spine.
  • Lease and occupier records with encrypted contact data
  • Rent payments with outstanding and overdue derivation
  • Service charge budgets and allocations
  • Dilapidation items linked to asset condition

Next step

Two conversations. Pick either.

See Artec Neo think — or tell us about the systems you already run and where an agent would earn its keep. Both start the same way.

No sales sequence, no gated PDF. A working session with the people who built it.