AdvancedIFS Applications 10 (on-prem)AI integration / Private architecture

IFS Applications 10 On-Prem AI Architecture: Keep Data on Site

Question
IFS Applications 10 AI integration on-prem

Also searched as

  • how to add AI to IFS Applications on-premises
  • IFS private LLM air-gapped
  • chat with IFS data Oracle
  • IFS Connect OData AI assistant

Short answer

IFS Applications 10 on-premises runs on an Oracle database behind an IFS middleware server, and it exposes data through logical unit views and APIs, IFS Connect messaging, web services and Aurena projections. A private AI layer reads a read-only Oracle copy, answers with a local open-weight model, and writes back only through supported IFS interfaces after human approval.

Applies to: IFS Applications 9 and 10 on-premises with Oracle. Aurena projection and OData availability depends on update level; check your release notes. IFS Cloud is a different architecture.

Add a private AI layer to IFS Applications 10 in seven steps

  1. 1Confirm release and update level, the Oracle edition and licences, and which sites and companies are in scope.
  2. 2Create a read-only Oracle copy for AI use: a physical standby opened read-only, or replicated tables or materialized views, after checking licence terms for the chosen feature.
  3. 3Build views over logical unit views such as SHOP_ORD, INVENTORY_PART_IN_STOCK, CUSTOMER_ORDER_LINE and PURCHASE_ORDER_LINE_PART, exposing only needed columns.
  4. 4Use IFS web services, IFS Connect or Aurena projections for record-level reads and for drafted transactions that a person approves.
  5. 5Index documents managed in IFS Document Management and file shares, with their access rules carried into the index.
  6. 6Serve an open-weight model with vLLM or Ollama on local GPUs and a gateway that logs prompts, tool calls and answers.
  7. 7Run phased rollout: read-only questions, then drafts, then approved actions through supported interfaces.

Data access paths in IFS Applications 10

IFS organizes data in logical units (LUs). Each LU has a table, a view that adds computed and translated columns, and a PL/SQL API package with the business rules. Familiar views include SHOP_ORD for shop orders, INVENTORY_PART_IN_STOCK for stock, CUSTOMER_ORDER_LINE for sales, and PURCHASE_ORDER_LINE_PART for purchasing. For reads, query the views, not the underlying tables, so state names and descriptions are translated correctly. Confirm view and column names in your dictionary.

For record-level access with business logic, IFS offers several routes: web services published from LU APIs, IFS Connect for message-based integration (XML and SOAP, with REST in newer updates), BizAPI in older releases, and Aurena projections that expose OData for the same data the client uses. Which are available depends on update level.

Writes must go through these supported routes, which call the LU APIs and apply validation, state transitions and events. Direct DML on IFS tables breaks state handling and is unsupported.

-- Read-only query on the Oracle copy (verify columns for your update)
SELECT order_no, release_no, sequence_no, part_no, contract, state
FROM   shop_ord
WHERE  contract = 'SITE1'
AND    objstate IN ('Released', 'Started')
FETCH FIRST 50 ROWS ONLY;

SELECT contract, part_no, location_no, qty_onhand, qty_reserved
FROM   inventory_part_in_stock
WHERE  contract = 'SITE1' AND part_no LIKE 'A1%';

Reference architecture, including air-gapped

Components: Oracle read-only copy; change data capture from redo using Oracle tooling such as GoldenGate or LogMiner based capture, or timestamp-based incremental pulls on views; retrieval index; tool server with named read actions; model server; audit log. The AI stack never connects to the production database.

The tool server exposes fixed, parameterised queries (for example "shop orders late by site") and a few record-level calls to web services or projections. The model chooses a tool and parameters; the gateway validates them and applies row and time limits.

For air-gapped plants, bring weights and images in on approved media, deploy the retrieval index and model server on the same network as IFS, and block all outbound routes. IFS Applications 10 does not need the internet to operate, so the AI layer need not either.

{
  "name": "ifs_late_shop_orders",
  "description": "Shop orders past need date for a site",
  "source": "shop_ord",
  "params": {"contract": "string", "days_late_min": "int"},
  "max_rows": 100,
  "mode": "read-only"
}

Permissions and write-back

IFS controls access through permission sets, per-user allowed sites and companies, and data access rules in some areas. The assistant must reflect these. Resolve the asker to an IFS user, then apply their allowed sites and companies as mandatory filters on every query against the copy. For anything the copy cannot express, call a web service or projection under that user so IFS evaluates the rights itself.

Write-back should be limited and approved: the assistant drafts a purchase requisition, a shop order operation report or a service request through a supported interface, shows the payload, and submits it after a named approver. The IFS audit trail then shows a person, and state-machine rules still apply.

Sizing and phased rollout

For 100 to 1,000 named users plan one or two data center GPUs for a 14B to 32B class model, and two 80 GB GPUs if you want a 70B class model for harder reasoning. Document indexes for maintenance manuals, drawings and procedures commonly run tens to low hundreds of gigabytes. Treat these as ranges to validate.

Phase 1: read-only questions on shop orders, stock, purchasing and service orders. Phase 2: drafts, such as shortage notes, maintenance summaries and supplier emails. Phase 3: approved actions through supported interfaces for a narrow set of transactions, with approvers and rollback rules.

Honest limits

IFS includes its own search, reporting and, in newer products, AI features. If you are moving to IFS Cloud, use the vendor path for new capabilities. For Applications 10 on-prem, a private layer is justified when you need cross-module questions, documents, or strict data residency.

Licensing for standby databases and replication features is your Oracle contract matter. Customisations, custom fields and custom LUs need mapping, and totals should come from SQL rather than the model. Do not assume OData projections exist on every update level.

Try it here, free

IFS Applications Oracle SQL Query Generator

Open full tool

Fill in site and part to get read-only Oracle SQL against common IFS Applications views for shop orders, stock and customer orders.

Common pitfalls

  • !Querying base tables instead of IFS views, losing state translations and computed columns.
  • !Running AI queries against the production Oracle instance during peak load.
  • !Writing with DML instead of supported APIs, bypassing state machines and events.
  • !Ignoring allowed-site and company rules so users see other sites.
  • !Assuming IFS Cloud interfaces exist in Applications 10.
  • !Forgetting to check Oracle licensing for standby or replication features.

How an ERP-grounded AI assistant handles this

ERPray can connect read-only to ERP data, show the query behind answers and respect roles, with on-prem options. For IFS Applications estates, Netray builds the Oracle copy views, tool server and approval flow with your IFS partner, using the interfaces your integrations already use.

See ERPray

Frequently asked questions

Can I add AI to IFS Applications 10 without the cloud?

Yes. Keep Oracle and IFS where they are, create a read-only copy, serve an open-weight model on local GPUs, and run the gateway inside your network. An air-gapped design has no outbound route.

Should I query IFS tables or views?

Query the logical unit views, such as SHOP_ORD or INVENTORY_PART_IN_STOCK, because they add computed columns and translated state names. Use web services or projections for record-level reads that need business logic.

How do IFS permissions carry over?

Map the asker to an IFS user, apply their allowed sites and companies as filters, and call web services or projections under their identity for anything views cannot express.

Is this the same as IFS Cloud?

No. IFS Cloud has a different architecture and vendor-provided AI path. This design targets IFS Applications 9 and 10 on-premises on Oracle.

Related

Advanced

How to Add AI to SYSPRO On-Prem Without Moving Your Data

SYSPRO runs on SQL Server with one database per company, and it exposes supported read and write paths through e.net Solutions business objects. A private AI layer reads from a read-only SQL Server copy, answers from a local open-weight model on your own GPUs, and writes back only through business objects after a human approves. Nothing has to leave your network.

Error fix

IFS Cloud: Unable to Save, Internal Server Error and Quick Report Problems

In IFS Cloud a save failure or internal server error is almost always a server-side exception returned through the projection the page calls. Read the error detail, reproduce it in the browser network tab, then check the middleware and database logs for the real cause, which is typically a business rule, a missing permission, a bad customization or a stale cache. Quick Report problems are usually a missing permission grant or mismatched bind parameters.

How-to

IFS Cloud Workflow Example, External File Templates, Update Analyzer and PO Status

Treat IFS Cloud configuration as a set of building blocks: workflows or business events to react to changes, external file templates to load or send flat files, an update analysis step to check what a release will touch in your customizations, and the supported database views for reading data such as purchase order status. This page shows how each fits together with a worked approval example.

How-to

IFS Cloud Report Designer, Quick Reports and Crystal Reports: Which to Use

IFS Cloud has several reporting routes. Use Quick Reports for fast read-only lists of data, the report designer route for formatted operational documents such as order confirmations and pick lists, legacy Crystal-based layouts only where you already have them, and the analytical tools for dashboards. Report rules then control when and how a report is produced and sent.

How-to

IFS Cloud: Add a Permission Set, What an IAM User Is and Linking an Employee to a Supervisor

An IAM user is the sign-in identity held in IFS Identity and Access Management, which authenticates the person. The IFS application user and its permission sets decide what that person may do. To add access, grant a permission set to the application user and make sure the identity maps to it; the supervisor relationship is an employee and organization setting, not a security one.

How-to

IFS Cloud Versions: Release Names, Solution Sets and How to Check Yours

IFS Cloud releases are named by year and half, such as 22R1 and 23R2, with service updates between feature releases. Solution sets are packaged industry or regional content layered on the core product, for example for aerospace and defense, Europe-specific needs or service industries. To see which version you run, use the About information in the client or ask your administrator for the installed release and update level.

AI for ERP

AI for IFS Cloud in aerospace and defense manufacturing

Add AI to IFS Cloud for aerospace and defense: projections, Aurena UX, Lobby, and engineer-to-order data, deployed on-prem or in your private cloud.

AI for ERP

A Private LLM Grounded on Your ERP Data

How a private LLM answers questions on your ERP data: RAG plus text-to-SQL, role-based permissions inherited from the ERP, and where each fits.

Stuck on IFS Applications 10 (on-prem)?

Talk to engineers who work inside IFS Applications 10 (on-prem) every week, and who build private AI that answers these questions from your own ERP data.

Talk to an ERP engineerBrowse ERP Help
All ERP Help articles

Keep exploring

Free tools

ERP fixes and how-tos

AI on your ERP

Integrations