Leveret SystemsOne connected data model — from CAD to the shop floor to the boardroom
Scaling manufacturers lose margin to disconnected CAD, spreadsheets and ERP. We build the digital thread — your systems structured around your ERP and joined to CAD and applied AI — so data flows cleanly from design, through build, to support. Fewer errors, faster quotes, one trusted view.
For regulated manufacturers
Stop re-proving certification evidence you already hold
Engineers lose hours hunting through prior submissions, standards and test reports for evidence that already exists. We build an assistant that answers from your own standards and your own past certification evidence — every answer cited to the governing clause, with a deterministic rules-engine gate in front of the generative layer. Deterministic where compliance demands it, AI-assisted where it saves time, human-signed-off throughout. A day or two on site for discovery; the build itself runs remotely in your own tenant. And the destination is bigger: bind the rules to the parametric values in your CAD models, and a configuration is checked as it is designed — the doorway to generative design within compliant bounds.
Your data stays yours. Pilots run inside your own cloud tenant wherever possible; otherwise in a UK-resident, single-client environment stood up for you alone. Your documents are never used to train models. At the end of the engagement everything is handed over or deleted — your choice, in writing.
What we build
The digital thread
One connected system, not a menu of tools. We structure your business around your ERP and integrate it with CAD and applied AI, so data flows cleanly from design, through build, to in-service support — the connective tissue that decides whether a scaling manufacturer keeps its margin. Very few people combine all three disciplines; each layer below is a live demo built from a real client system.
Why Leveret
Three disciplines, one accountable partner
This is not a systems contract; it is a strategic capability — and very few people combine the three disciplines the digital thread needs. One partner spanning design, build and through-life means the foundation is built knowing where it has to go: no re-work, nothing lost between suppliers, one point of accountability for the outcome.
Business systems & integration
20 years across construction and manufacturing, hands-on with APIs, event-driven middleware and data flows. On the last manufacturing engagement, fragmented legacy tools were replaced with a unified platform of ~78 integrated endpoints across sales, manufacturing and web.
CAD integration
Engineering-data and CAD pipelines (Autodesk APS / SolidWorks) that connect the design model to the business systems and shop floor that turn it into product — and, at the far end, bind the model's parametric values to the compliance rules so a design is checked as it is drawn. MSc BIM & Integrated Design; seven years in digital-engineering development.
AI architecture
Production AI on a "generative components between deterministic gates" principle — retrieval-augmented and agentic systems with responsible-AI guardrails and mandatory citation, including a clause-cited rules-engine-plus-RAG for regulatory compliance. MSc Data Science & AI (Distinction).
From source file to factory floor
Real models translated through Autodesk Platform Services and recorded straight from the SVF2 viewer. Fusion, Revit, IFC, point clouds — the same pipeline, drives our customers' Bills of Materials, work orders and digital twins.
Who we are
The Team
Leveret Systems is led by Eben Joubert — an engineer with a background in CAD pipelines, cloud data platforms and production AI. Every engagement is principal-led: the person you speak to is the person who designs and builds the system. Where a project needs more hands, specialists come in from an established associate network.
MSc Data Science & AI (Distinction) · MSc BIM & Integrated Design · 20 years across construction and manufacturing engineering.
Eben Joubert on LinkedInSystems Architecture & Development
20+ years experience
Enterprise platform design, full-stack development, system integration, and cloud architecture. Deep expertise in construction technology, manufacturing, and CAD-driven product lines.
Data Analytics & Business Intelligence
15+ years experience
Business analysis, BI development, data team leadership, and machine learning. Advanced qualifications including MSc Data Science. Track record at major enterprises in banking, telecoms, and fintech.
Software Engineering & DevOps
10+ years experience
Backend engineering, API design, CI/CD pipelines, and infrastructure automation. Experience across high-throughput platforms, real-time systems, and cloud-native microservices.
Selected work
Case Studies
The digital thread in production. Open any one for the full breakdown — the first is the clause-cited compliance assistant that the certification-evidence pilot is built on; the others connect CAD, ERP-class data and BI on one model.
AI in production
Six AI agents shipped — running every day, in production
Each one is a generative component between deterministic gates — the gates decide; the model only drafts.
Two-pass classification on every inbound — intent, sentiment, entities, draft reply.
Native Revit properties + position rules → 38 derived element classes.
Predicts slip risk per supplier from historical lead-time variance + live signals.
Unifies every GA4 session, quote, email and CRM event per customer — semantic match.
Turns a customer enquiry into a draft quote with line items priced from catalogue.
Reviews every internal PR against codebase conventions + flags risky migrations.
AI engineering
How we keep AI consistent in production
Architectural principles
Engagement
Pricing
Most engagements start small: a fixed-price, four-week pilot at £12,500 on one product family, so you see the value on your own data before committing to anything larger. From there, one lead and one blended rate, with intensity that flexes as the system matures — a typical embedded engagement runs to roughly £140,000 a year. Capacity flexes; the rate does not escalate between stages.
Engagement shapes
Day rates
Who it's for
Where the digital thread pays off
Aerospace & Cabin Interiors
Certified programmes: CAD-driven configuration, airworthiness/TSO evidence, weight roll-up and as-built traceability.
Configured & Engineer-to-Order Products
CAD-to-quote — BOM, weight, cost and lead-time generated from the model; catalogue, options and pricing kept in sync.
Precision & Composite Manufacturing
Engineering BOM to manufacturing BOM with no re-keying; engineering-change control and shop-floor data capture.
Industrial Equipment & Machinery
Design-to-build-to-service on one data model; spares, warranty and in-service data turned into a profit centre.
Construction & AEC
The same connected-data discipline in BIM/CDE — ISO 19650, Autodesk APS, digital engineering.
Medical Devices
Technical files and design history: cited retrieval across standards, test evidence and prior submissions; traceability from requirement to as-built.
ATEX & Pressure Equipment
Conformity evidence: find and re-use prior assessments, cited to clause; keep the technical file consistent with the CAD model.
Rail & Marine
Certification and survey evidence: one searchable, cited view of standards, approvals and past submissions for each product family.
Process
How we work
Discovery call
We understand your problem, systems landscape, and goals.
Architecture & scope
A clear proposal with architecture, timeline, and fixed or day-rate pricing.
Build
Iterative delivery with weekly demos — you see progress from week one.
Launch & support
Deployment, training, documentation, and ongoing support options.
Get in touch
Start a conversation
Tell us which product family eats the most certification-evidence hours, and you will get a straight answer on whether the four-week pilot fits. Or, for the wider digital thread, just start the conversation.