AdvancedDassault ENOVIA (on-prem)Private AI layer / MQL / 3DSpace

How to add AI to ENOVIA and on-prem 3DEXPERIENCE

Question

how to add AI to ENOVIA on-prem

Also searched as

ENOVIA AI integration without cloud
ENOVIA MQL query for AI assistant
3DEXPERIENCE on-prem private LLM
chat with ENOVIA data on-premises

Short answer

Read ENOVIA data through supported interfaces: MQL and the Java API (matrix.db.Context, JPOs) on the kernel, or the 3DSpace web services where deployed, always in the context of the asking user's person and security context. Serve an open-weight model on local GPUs and index documents locally, so Dassault's role and policy model keeps deciding what is visible.

Applies to: ENOVIA V6 and on-prem 3DEXPERIENCE (R20xx releases) with Oracle or SQL Server. Cloud 3DEXPERIENCE on Dassault's platform follows a different path.

Reference build for a private AI layer on ENOVIA

1List question classes: part, document and engineering item lookup, structure and where-used, lifecycle state and policy, change actions, and content Q and A over attached documents.
2Choose the interface per class. Use JPOs or Java API reads for custom schema, and the 3DSpace web services for standard modelers where they are deployed and secured on your platform.
3Build a tool server with named read actions that open a Context for the asking user, run bounded MQL or API calls and return structured results with object ids.
4Extract text from document files held in ENOVIA file stores via a worker, store type, name, revision, policy and state with every chunk, and keep an access marker.
5Serve a local open-weight model with vLLM, local embeddings and a local vector index. No outbound route from the model host.
6Carry the user's identity and security context into every call. Log all tool calls and the bus object ids returned.
7Phase in read-only Q and A first, then drafted change actions and review summaries, then supported lifecycle promotes and creates after approval.

Data access paths in ENOVIA

ENOVIA's kernel stores business objects (types, names, revisions), relationships, attributes, policies with states, and person, role and security context definitions. The native query language is MQL, and the Java API exposes the same model through classes such as matrix.db.Context and BusinessObject. Custom behaviour is usually written as Java Program Objects (JPOs) invoked by the kernel.

Do not read the underlying Oracle or SQL Server tables directly. The storage layout is internal to the kernel and bypasses access rules. On 3DEXPERIENCE platforms, the 3DSpace web services provide REST access to standard modelers behind 3DPassport authentication, and 3DSearch can provide index driven retrieval where deployed.

temp query bus Part * * where "current==Released" limit 50 select id name revision description current dump |;

// Java sketch: open a context as the asking user and run a bounded MQL read
Context ctx = new Context(serverUrl);
ctx.setUser(userName);
ctx.connect();
String out = MqlUtil.mqlCommand(ctx, "temp query bus Part A-10045 * select id revision current dump |");

Reference architecture

Place the components in the same enclave as the ENOVIA application server: a tool server using the Java API or web services, a document extraction worker, a vector index, a GPU host and an audit store. Optionally use a reporting copy of the database for aggregate questions you have validated against MQL results, since schema meaning depends on your data model customisation.

Change feeds are not standard. Plan scheduled re-indexing by modification date per type, plus triggers or event hooks for lifecycle promotions if your team already maintains triggers for integrations. In an air-gapped site everything, including weights and packages, enters by controlled media.

Permissions, security contexts and write-back

ENOVIA authorises users by person, role, organisation and project in a security context, then applies policy state access, ownership and any ABAC style rules your implementation adds. Opening a Context for the real user with the right security context makes the kernel enforce this, which is why the tool server must not use a shared administrator login.

For writes, use the same Java API or web service operations the applications use: create a change action, add a note, or promote a state through supported calls so triggers and policy checks fire. Show the user the exact payload, run under their identity, and log the resulting object. Do not let the model run raw MQL that modifies objects.

Sizing, limits and honest trade-offs

A pilot for 25 to 60 engineers typically fits one to two GPUs of 48 to 80 GB. Wider rollout to several hundred named users plans two to four GPUs, separate CPU capacity for extraction, and an index of tens of GB for a few hundred thousand documents. Treat these as planning ranges and validate with a concurrency test.

Limits: heavy customisation means object names and attributes differ per site, so tool actions must be written against your model. Geometry and simulation data are not readable by a text model. If your users are already on cloud 3DEXPERIENCE and can use Dassault's own assistants, those may be enough; the private layer pays off when the platform is on-prem and the data cannot leave.

Try it here, free

ENOVIA Private AI Layer Blueprint Generator

Open full tool

Create a shareable plan for adding a private AI assistant to on-prem ENOVIA or 3DEXPERIENCE using MQL, the Java API or 3DSpace web services.

Fill in

Company name

Platform release

Database engine

Hosting

Named users

Sites or plants

Main use cases

Data that must never leave the site

GPU available

Target go-live

Live preview

Download:

ENOVIA Private AI Layer Blueprint Generator

1. Context

Meridian Propulsion Corp runs 3DEXPERIENCE R2023x on Oracle (Air-gapped). 500 named users across 4 site(s). Target go-live: 2027-06-30.

Use cases: Engineering item and structure queries, change action impact, document Q and A, lifecycle state questions.

Must stay on site: Export controlled technical data, program designs, supplier proprietary data.

2. Components

Component	Design for 3DEXPERIENCE R2023x	Notes
Data access path	MQL and Java API (Context per user) or JPOs for custom schema; 3DSpace web services where deployed	No direct reads of kernel tables
Retrieval index	Local index over document files and object metadata with type, policy, state and revision on each chunk	Re-indexed by modification date per type
Model serving	Open-weight model on vLLM, GPU: 4 x 80 GB or more	Local embeddings and reranker
Tool server	Named actions: find object, expand structure, where-used, change action impact	Parameterised, read-only
Identity and permissions	Person, role and security context of the real user; policy state access applied by the kernel	Live re-check before display
Audit	Log of user, security context, calls, object ids and answer	Immutable store

3. Security controls mapped to your inputs

Hosting: Air-gapped. Weights, packages and updates arrive by controlled media and the model host has no outbound route.

For Export controlled technical data, program designs, supplier proprietary data.: contexts are opened per user with their security context; indexed text carries policy and state and is re-verified before display.

No model-composed MQL that modifies objects. Phase 3 writes use supported operations so triggers and policy checks fire.

4. Rollout

Phase	Scope	Exit criteria
1: Read-only	Object, structure, change and document Q and A for one program	Accuracy on a reviewed set of questions
2: Drafts	Change action summaries, review packs	Reviewer acceptance
3: Approved actions	Supported creates and promotes with approval	Trigger behaviour tested in non-production

5. Open questions for IT

1. Which types, policies and attributes are customised? 2. Are 3DSpace web services deployed and secured? 3. How does 3DPassport or SSO map to ENOVIA persons? 4. Where are file stores and what read path may extraction use? 5. Which triggers fire on writes?

Prepared by / Date

PLM owner / Date

IT security / Date

A starting plan. Heavily customised ENOVIA models differ per site, so confirm every type, policy and attribute name with your administrators.

Plan review for ENOVIA

Optional: a short review of your plan with attention to security contexts and custom schema.

Optional. The tool and every export work without this. No spam.

Common pitfalls

!Using one super-user Context for the integration and losing per-user security.
!Running free-form MQL composed by the model. Offer parameterised, read-only actions.
!Ignoring policy and state when quoting content, so an In Work revision looks like a released one.
!Querying kernel tables directly. Their layout is internal and bypasses access control.
!Assuming type and attribute names from a demo database. Production models are customised.
!Forgetting that triggers run on writes. Test write actions in a non-production environment first.

How an ERP-grounded AI assistant handles this

A grounded assistant on ENOVIA answers 'which released parts are affected by this change action' by running bounded reads as the user and presenting the objects with state and revision. Netray builds this as a private layer with local models, mirrored security and an audit log, delivered with Dassault-skilled partners where the data model is heavily customised.

See ERPray

Frequently asked questions

MQL, JPO or web services: which should I use?

Use web services for standard modelers if they are deployed and secured on your platform, and MQL or JPOs for custom schema and exact control. Whichever you pick, wrap it in a named action in the tool server and keep it read-only.

Does this apply to cloud 3DEXPERIENCE?

Not directly. This design targets on-prem ENOVIA and 3DEXPERIENCE where you operate the servers and control the data boundary. Cloud deployments have different APIs, tenancy and data residency questions.

How are security contexts handled?

The tool server opens a Context for the real user with the matching security context, so the kernel applies its normal checks. Indexed chunks hold type, policy and state, and are re-verified by a live read before display.

Can the assistant promote lifecycle states?

Only as a proposed action that the user approves, executed through supported calls under their identity so triggers and checks fire. Autonomous promotion is not recommended for controlled design data.

Advanced

How to add AI to Teamcenter on-prem without moving your PLM data

Run an open-weight model on your own GPUs, expose a small set of read-only Teamcenter actions through a tool server that calls the Teamcenter SOA web services as the asking user, and index documents and datasets locally. Teamcenter's Access Manager keeps deciding who sees what, so the assistant cannot show a user anything their own session could not open.

Advanced

How to add AI to Autodesk Vault on-prem using the Vault API

Use the Vault web services API to read files, properties, items and change orders as the asking user, extract document text through the Job Processor or a service, and serve an open-weight model on your own hardware. Vault's roles, folder access control and lifecycle state security stay in force because every read goes through the server.

How-to

How to send a Windchill BOM to your ERP

Release the BOM from Windchill on an approved change, not on demand. Use PTC's Enterprise Systems Integration (ESI) for a managed release to SAP or Oracle-class ERPs, or build the feed on Windchill REST Services (OData) for other targets. Map part, structure, revision and effectivity explicitly, and make the ERP response visible back in Windchill.

Advanced

How to add a private AI layer to Infor LX / BPCS on-prem

BPCS and Infor LX run on IBM i with their data in Db2 for i, in files that carry short coded names by module. A private AI layer reads those files through read-only SQL views over a replica, indexes documents and attachments separately, exposes approved queries through a tool server, and serves an open-weight model on local GPUs. Writes, if any, go through the supported transaction programs with human approval.

Advanced

How to add a private AI layer to Infor System21 on-prem

System21 runs on IBM i with its business data in Db2 for i. The practical private AI pattern is a read-only replica or extract, SQL views that give files readable names, a retrieval index over documents, a tool server of approved queries, and a locally served open-weight model. User visibility is carried over from System21 security and company set-up, and writes only go through its supported entry points after approval.

Advanced

How to add a private AI layer to Infor EAM on-prem

On-prem Infor EAM stores its data in an Oracle or SQL Server schema whose tables use the R5 prefix, and it exposes web services for supported access. A private AI layer reads equipment, work order and parts data through read-only views on a reporting copy, indexes failure notes and manuals for retrieval, mirrors EAM organisation security, and serves an open-weight model locally. Work orders created or changed by the assistant go through EAM's web services after a person approves.

AI for ERP

Stuck on Dassault ENOVIA (on-prem)?

Talk to engineers who work inside Dassault ENOVIA (on-prem) every week, and who build private AI that answers these questions from your own ERP data.

Talk to an ERP engineer Browse ERP Help

All ERP Help articles

Keep exploring

Free tools

AI on your ERP

AI for 3DEXPERIENCE and ENOVIA That Works With Your Business Objects, Not Around ThemAdd private, grounded AI to Dassault 3DEXPERIENCE and ENOVIA: query parts, engineering changes and documents through 3DSpace web services without exposing IP.

Software

3DEXPERIENCE ENOVIA3DEXPERIENCE ENOVIA explained: Dassault Systemes PLM capabilities, typical modules, CATIA and ERP integrations, strengths, limits and alternatives.

How to add AI to ENOVIA and on-prem 3DEXPERIENCE

Reference build for a private AI layer on ENOVIA

Data access paths in ENOVIA

Reference architecture

Permissions, security contexts and write-back

Sizing, limits and honest trade-offs

Fill in

ENOVIA Private AI Layer Blueprint Generator

1. Context

2. Components

3. Security controls mapped to your inputs

4. Rollout

5. Open questions for IT

Plan review for ENOVIA

Common pitfalls

How an ERP-grounded AI assistant handles this

Frequently asked questions

Related

How to add AI to Teamcenter on-prem without moving your PLM data

How to add AI to Autodesk Vault on-prem using the Vault API

How to send a Windchill BOM to your ERP

How to add a private AI layer to Infor LX / BPCS on-prem

How to add a private AI layer to Infor System21 on-prem

How to add a private AI layer to Infor EAM on-prem

A Private LLM Grounded on Your ERP Data

AI Agents for ERP, Running On-Prem

On-Prem AI for ERP in Aerospace, Defense, and Electronics Manufacturing

Stuck on Dassault ENOVIA (on-prem)?

Keep exploring

Free tools

AI on your ERP

Software

Fill in

ENOVIA Private AI Layer Blueprint Generator

1. Context

2. Components

3. Security controls mapped to your inputs

4. Rollout

5. Open questions for IT

Plan review for ENOVIA