Industry agent in preparation: Construction, engineering and infrastructure
Run the project on governed AI.MeshBuild is ASG™, the Arrochar Superintelligence Guardrails, packaged for construction, engineering and infrastructure.
The suite packaged for the operations of a contractor, an engineering firm or an infrastructure owner: tenders and contracts, design and change control, site safety, subcontractors and workforce, plant and equipment, progress claims and variations, quality and defects, environmental and heritage obligations and the reporting a safety regulator and a client expect, as governed AI agents that never sign off a design or certify a structure.
For contractors, engineering firms, infrastructure owners and operators, building-materials suppliers, equipment hire companies and the safety and planning regulators they report to.
What exists today, and what does not
This package is named and its scope is written. The service catalogue, the service pages, the agents, the gates and the evidence records are not yet built, and nothing runs for a customer. The rails it will run on, AIG Sentinel and Meshbone, exist today and are the same rails MeshGov runs on. When the first service is built we will say which one, and until then the status on this page stays as it is.
What the MeshBuild catalogue is being written to cover
The operations of construction, engineering and infrastructure, as governed AI services. Each line below will become one or more services in the catalogue, with its own page naming the agents, the decisions that stay with a person, the records it keeps and the standards it is mapped to. Until then this is scope, not a product.
- Tenders, contracts and variations: the bid, the contract record, the notices each clause requires and the variation priced and approved by a person
- Design and change control: drawings, revisions, requests for information and the approvals that release a design for construction, each signed by the responsible engineer
- Site safety: inductions, permits to work, high-risk work licences, hazard reports, incidents and the statutory notifications that follow
- Subcontractors and workforce: prequalification, insurances, competencies, security of payment obligations and site access
- Plant and equipment: hire, inspections, certifications, maintenance and the utilisation record
- Progress claims, payment schedules and the three-way match, within each jurisdiction's security of payment rules
- Quality, inspection and test plans, defects and handover: the hold points witnessed by a person and the record the client receives
- Reporting to the client, the safety regulator, the planning authority and the board, from one evidence chain
The baseline we expect to align to
Construction has no single reference architecture the way banking has BIAN. We expect to align the information exchanged about the asset to the ISO 19650 series for building information modelling and to the buildingSMART openBIM standards (IFC), to align asset management to ISO 55001 and project and portfolio management to ISO 21500, and to take each jurisdiction's work health and safety, security of payment, building and planning legislation as the policy source. Arrochar Labs is not a buildingSMART or ISO member, and neither has reviewed anything here. MeshBuild is an operations package. It will not sign off a design, certify a structure or take a safety decision on site, and no service in the catalogue will be written to. The choice of baseline is not final and will be stated on the service pages when the catalogue is published.
The same way as MeshGov and MeshFin
Every industry agent follows one formula. AIG Sentinel defines the policy, Meshbone enforces it at run time, Nanolitte carries the controls into reusable service templates, Databallast controls what data the agents may access, agentVIKING™ guards every agent, and the evidence chain records what happened. The catalogue for this industry will name its services, the decisions that stay with a person, and the standards it is mapped to, service by service, exactly as the MeshFin catalogue does for banking. Once the catalogue is published, MeshAgentDesigner shapes the pack to one organisation: by watching the work, by reading a drawing, or by configuration.
How it fits together
A complete suite of AI governance agents. An architecture that makes them accountable.
Each part of ASG™ does one job, in order, and hands the next part something it can check. That is the difference between building AI agents and running them so an auditor, a regulator or a minister can see what happened.
Before the first build, Orbit Roadmaps finds where AI creates value and profiles the risk.
After it, Execdive turns what the chain recorded into plain-language insight for executives.
Policy, enforcement, templates, data, controls, evidence. Then services.
This describes the architecture, not what every deployment runs today: 5 of the 27 agentVIKING™ controls are still in development.
- AIG Sentineldefines policy
- Meshboneenforces policy at run time
- Nanolittecarries the controls into reusable service templates
- Databallastcontrols what data the agent may access
- agentVIKING™is the control set across every agentAcross every step
- Evidence chainrecords what happened
- MeshGovuses the whole thing for government services
- MeshFinuses the whole thing for banking and financial services
The other industry packages
Shape the catalogue with us
If you run operations in this industry and want to see your own services on the list, talk to us. Early conversations decide which services are built first.
Talk to us about MeshBuild