AdvancedBaan IV and Baan 5 (legacy)AI integration / legacy Baan data access

Private AI Layer for Baan On-Prem: Reference Architecture

Question
how to add AI to Baan IV or Baan 5 without migrating

Also searched as

  • Baan ERP AI integration
  • chat with Baan data on-prem
  • Baan 5 ODBC read-only AI assistant
  • Baan legacy modernization with private LLM

Short answer

For legacy Baan, do not touch the application. Copy data to a read-only reporting database on a schedule, index documents locally, expose approved read actions through a tool server, and serve an open-weight model on your own GPUs. Baan's table naming and authorisations must be mapped by hand, and writes should stay in Baan sessions.

Applies to: Baan IV and Baan 5 / BaanERP on Unix or Windows with Oracle, Informix, SQL Server or the Baan database driver

How to build a private AI layer on Baan

  1. 1Confirm the Baan version, operating system, database and whether a supported driver or export path exists.
  2. 2Pick the tables and companies that answer your target questions and export them to a read-only reporting database on a schedule.
  3. 3Capture Baan data dictionary names and domains so labels and enumerated values read correctly in the index.
  4. 4Index reports, drawings and documents from file shares with local embeddings.
  5. 5Expose approved read actions through a tool server over the reporting copy only.
  6. 6Serve an open-weight model on local GPUs and log every prompt and query.
  7. 7Keep write-back inside Baan sessions: the assistant drafts, a user enters or approves in Baan.

Data access paths in Baan

Baan uses package, module and number table names such as tcibd001 for items, tdsls040 for sales orders and tdpur040 for purchase orders in Baan IV, with LN-style names (for example tdsls400) in later Baan 5 and LN lineages. Verify against your own data dictionary because customisations and versions differ. In the database the table name carries the company number.

Access options depend on version and platform: the Baan database driver and ODBC access on Windows, native database access when Baan data sits in Oracle or SQL Server, session-based exports and ASCII dumps, and Baan's own business interfaces where the site has them. Choose the least intrusive one that your Baan version supports, and always read from a copy.

Enumerated values are stored as numbers whose meaning lives in the domain definitions, so export those as lookup tables or the model will return raw codes.

-- Reporting copy, read-only (names are from the Baan data dictionary, verify on your system)
SELECT t_item, t_dsca, t_citg
FROM tcibd001100
WHERE t_citg = 'RAW';

Reference architecture

Treat Baan as a data source and a system of record you do not alter. A scheduled extract writes to a reporting database; a document pipeline indexes reports and drawings; a tool server exposes a short list of named read actions; a model server on local GPUs answers; an audit store records everything.

Because Baan IV era servers may be unsupported or fragile, keep extracts off peak, and never run vector search or analytics against the production database. Air-gapped sites simply keep the whole stack inside the boundary.

This pattern also supports migration: the same reporting copy and index become the reference for validating a later move to LN or another ERP.

Permissions and write-back

Baan authorisations are by user, role and session, with company partitioning. They are not exposed through a modern identity API, so the tool server must carry its own role map: for each person, which companies and data classes they may query, maintained alongside Baan's own definitions.

Write-back: keep it in Baan sessions. The assistant can produce a drafted order change or an item review checklist, but a user keys or imports it through standard Baan sessions or an approved import mechanism, never by direct table writes.

Sizing, limits and honest caveats

Baan estates are often smaller in users (50 to 300 named) but large in history, so the index of documents and extracts matters more than concurrency. One inference GPU usually covers the interactive load; plan a second for redundancy.

Limits: the data is only as fresh as your extract schedule, tooling for Baan IV is thin, and customisations undocumented in the dictionary will confuse retrieval. If the real aim is replacing Baan, the assistant helps analysis but does not replace migration.

Try it here, free

Baan Private AI Layer Blueprint Generator

Open full tool

Fill in your Baan environment and get a ready-to-share architecture plan for a private, on-prem AI assistant.

Common pitfalls

  • !Running extracts or queries against production during peak shifts on aging hardware.
  • !Returning raw numeric domain codes because enumerated values were not exported.
  • !Forgetting the company suffix and mixing data from multiple companies.
  • !Assuming Baan IV and Baan 5 share identical table names and fields.
  • !Writing to Baan tables directly instead of using sessions or supported imports.

How an ERP-grounded AI assistant handles this

DataRay and ERPray can sit on a reporting copy of Baan data, show the query behind each answer, and run on your own GPUs. Netray treats Baan as read-only and keeps changes inside Baan sessions.

See ERPray

Frequently asked questions

Can I add AI to Baan without migrating?

Yes. A scheduled read-only copy, a local document index and a tool server in front of an open-weight model give natural-language access without changing Baan or sending data out.

Is there an API for Baan?

It depends on version and platform: database driver or ODBC access, exports and, in later versions, business interfaces. Choose the least intrusive supported path and read from a copy.

How do I handle Baan roles?

Baan roles are not available as a modern identity feed, so maintain a role-to-company-and-data map in the tool server and filter every query and retrieval by it.

Will the AI work on old Unix servers?

The model does not run on them. Extract data to a modern reporting server; AI runs on separate GPU hardware on your network.

Related

Error fix

Infor LN: BOD mapping errors when publishing to ION

This error means the outbound Business Object Document from LN could not translate a field, code, or reference value into the ION-standard BOD schema, most often a missing code list mapping or an unmapped custom field, not a bug in ION itself. Fix the mapping on the correct side and reprocess from ION Desk rather than resending from LN.

Error fix

Diagnose and fix a failed BOD document flow in ION Desk

A Document Flow showing Failed in ION Desk means a BOD (Business Object Document) stopped either at schema validation, at the mapping step, or at the target application. Open the failed instance's detail to see the exact failing element, fix the source data or mapping, then use Resubmit rather than re-triggering the original transaction to avoid duplicates.

Error fix

Infor LN bshell Process Stuck at 100% CPU: How to Diagnose and Fix It

A bshell process pinned at 100% CPU on the Infor LN application server almost always means one session is stuck in a 4GL loop, scanning an unindexed table, or waiting on a database lock. End the session from the Sessions Monitor first, then kill the OS process only if that fails, and check for a blocking database transaction before assuming it is a bug.

Error fix

Infor LN Not Authorized to Run This Session: How to Fix It

Infor LN refuses to open a session with a not authorized message when the logged-in user's assigned role does not include that session, or when the session is blocked for the company they are logged into. Grant the session through Common > Authorization Management > Roles, or check the user's role and company context, and the session opens on retry. In most cases this is a permissions configuration issue, not a bug.

Error fix

Infor LN DAL Out of Sync After a Custom Field: Cause and Fix

Infor LN throws a DAL, or table, out of sync error, or simply drops a new custom field silently, when a table's dictionary definition is changed but the generated DAL and dependent forms are not regenerated afterward. Running the standard sequence, table compile, DAL generation, then session/form compile, in Tools > Development after every dictionary change resolves it. Skipping any one of the three steps is what causes the mismatch.

Error fix

Infor LN Jobs Stuck in Active or Waiting: Fix the Job Daemon

Infor LN background jobs, reports, batch processes and print jobs, get stuck in Active or Waiting status when the job daemon on the enterprise server has stopped or lost its connection, or when a prior job crashed without releasing its status. Restart the job daemon and reset the stuck job's status through the Jobs session, and the queue resumes. A daemon that keeps stopping usually points to a memory, license or database connectivity problem on the server.

AI for ERP

AI for Legacy Baan IV/V: Capture the Knowledge Before It Walks Out the Door

Use AI to capture knowledge from ageing Baan IV/V systems, document undocumented customisations, and de-risk a future migration to LN or CloudSuite.

AI for ERP

AI for Infor LN: Sessions, BODs, and Engineer-to-Order Work

Add grounded AI to Infor LN 10.x or CloudSuite: natural-language answers over sessions and BODs, agents for project and engineer-to-order work, on-prem options.

Stuck on Baan IV and Baan 5 (legacy)?

Talk to engineers who work inside Baan IV and Baan 5 (legacy) 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

Guides

AI on your ERP

Integrations

Comparisons

TermsBaan IVBaanERP (Baan V)Infor LNPorting SetBshellTable Sharing