Engineering Context Infrastructure for Industrial AX
LAPIS3D connects P&IDs, 3D models, document clauses, requirements, and change history so AI agents can understand real engineering objects and review design.
Tag Resolver finds the real 3D object a document or drawing tag points to. Spatial Resolver finds the space and relationships around it that need review. The AI agent applies document clauses and design requirements to the real model, and the result is captured as an Evidence Snapshot.
Not AI that finds documents — AI that understands and reviews real design.
SmartPlant P&ID Database
or Engineering Lists
Documents & change history
revisions + document clauses
Smart3D & key 3D engineering models
primary · alternatives
Design basis & requirements
requirements + constraints
DEXPI 2.0 Normalization
Process Rich Tag Graph
identity · relationships · topology
Spatial Intelligence
Spatial Graph
identity · hierarchy · relationships · metadata
Shared identity + provenance
humans and AI see the same basis
Tag Resolver
finds the real object a tag points to
Spatial Resolver
finds the space and relations to review around it
AI-assisted design review
Links document clauses and design requirements to real objects and space for review
The AI agent reviews relevant clauses, requirements, target objects, and surrounding space together to analyze design conformance and change impact.
Evidence Snapshot
records the document clauses, objects, revisions, Viewpoints, and judgment basis used in the review
Pain points
Smart3D mega-models take so long to fully re-extract and redistribute that sharing the latest model lags. S3DX incrementally updates only what changed, so the latest 3D model can be deployed quickly. HQ, site, and partners can share and review design against a fresh model every day.
Drawings, 3D models, document clauses, and requirements sit apart, so engineers must find targets and confirm relationships by hand. LAPIS3D lets an AI Agent understand Engineering Context, linking document clauses to real objects and space to support repetitive design review and impact analysis.
Knowing only what changed in a new revision is not enough to judge design impact. LAPIS3D connects changed objects to tags, P&ID relationships, and surrounding 3D space to analyze the impact scope of Revision Deviation. Engineers can see both the before/after difference and what needs review.
Screenshots and comments alone make it hard to revisit which model revision, objects, document clauses, and space informed a judgment. Evidence Snapshot records the Viewpoint, objects, revision, requirements, and judgment basis from the moment of review. You can trace and share not only the result but why it was judged that way.
Even for the same equipment, P&ID and 3D model names, hierarchies, and data structures can differ. Tag Resolver uses Engineering Identity and model context to find the real 3D object a tag points to. People and AI Agents analyze and review design against the same target.
EPCs and Owner Operators mostly run design data On-prem. nanochat uses Engineering Context and GraphRAG to reduce large-LLM load and run local AI Agents on existing CAD workstations, lowering added GPU infrastructure dependence and cost.
LAPIS3D solves these problems with Engineering Context.
Explore industry workflows →The context layer
Process Rich Tag Graph connects engineering identity, process semantics, and records. Spatial Graph connects objects, hierarchy, spatial relationships, and geometry. Shared identity and provenance keep them on the same page.
Process Context
We collect data from the SmartPlant P&ID Database or key engineering lists, normalize objects, attributes, identifiers, and relationships against the DEXPI 2.0 specification, and build a Process Rich Tag Graph. Different sources can then be interpreted through the same Engineering Identity and Process Context.
Spatial Context
The Spatial Graph is built from Smart3D objects, hierarchy, position, relationships, and metadata — and, where needed, from other key 3D engineering models.
Humans read this through P&IDs, drawings, 3D, timelines, and Evidence Snapshots. AI reads the same identities, graphs, metadata, and provenance.
The differentiator
Tag Resolver resolves engineering identity to the authoritative target object. Spatial Resolver interprets engineering intent through Spatial Graph and qualified spatial rules to find the relevant neighborhood and relationships.
Identity
Authoritative tag context, 3D naming patterns or regex, hierarchy, and model context resolve toward the target 3D object. Where ambiguity remains, it returns confidence, a candidate set, provenance, and a human review path.
Context
Engineering intent, the identified object, Spatial Graph, and qualified spatial rules produce the neighborhood an engineer actually needs to review. It is not proximity search, nearest-neighbor search, or scene-graph traversal.
From document retrieval to object resolution. From object resolution to spatial reasoning.
Evidence Snapshot
An Evidence Snapshot is a portable engineering context package, not a screenshot. It links the view, object identity, tag, revision, requirement or clause, markup, review context, provenance, and spatial rule attribution where applicable.
Evidence Snapshot makes the decision legible.
Evidence package
Evidence Snapshot
Portable is a design direction. The package format and cross-system portability are not finalized claims.
Two execution surfaces
Browser collaboration and on-prem execution are deployment choices, not competing realities. Both work from the same engineering context.
Engineering Context Workspace
A browser workspace where multidisciplinary teams and AI review 1D, 2D, and 3D against the same context. Evidence and CRS workflows stay connected to the objects and revisions under review.
A local AI agent on existing CAD workstations
Combining SLM with Engineering Context, it understands drawings, 3D models, requirements, and change history on internal networks and in the field, supporting design review.
Products
Each product owns a distinct part of the engineering context. None of them replaces the source of truth.
Process context from P&ID and engineering records.
Spatial context and 3D Tiles infrastructure for engineering models.
Engineering deliverables, coordinate-true 2D backgrounds, and evidence.
An AI/LLM-assisted engineering view across 1D, 2D, and 3D.
A local engineering agent runtime for the CAD workstation.
Engineering insights
Short, practical notes on context, change, spatial reasoning, and industrial AI. Leave with an engineering insight, not a product pitch.
The problem with change in EPC is not the change itself. It is proving why it changed, when it changed, and what it affected.
Read the insightA model can show shape without process meaning, relationships, or revision. Spatial context is the engineering layer around the geometry.
Finding a document is not the same as resolving the object, its relationships, and the neighborhood an engineer must review.
Restricted networks and on-prem engineering data are not edge cases. They are design constraints for industrial AI.
The practical value is not a finished drawing. It is an engineering-ready 2D background that lets detailed design move faster.
Customer influence
Not a logo wall. These are the engineering pressures that shaped how we build.
Practical engineering at scale.
Shipbuilding-scale models and real engineering workflows reinforced that engineering software must work in production, not only in demos.
Engineering software must reflect real workflows.
Engineering under real site constraints.
Work for a major global refinery operator in the Middle East drove the need for offline and restricted-network deployment, on-prem execution, and local AI.
Industrial AI cannot be cloud-only.
From model view to engineering deliverable.
A practical engineering need helped inspire the direction behind L3D Emit: turning 3D model views into engineering-ready 2D backgrounds.
Model-to-drawing automation matters.
Additional long-standing customer relationships across EPC, energy, and shipbuilding are represented separately from product-shaping stories.
Tell us about the review or improvement you need. We will work out how to connect your data and propose a workable scope.
