AdvancedInfor System21 (IBM i)Private AI / Integration Architecture

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

Question
Infor System21 AI integration on-prem

Also searched as

  • System21 AS/400 AI assistant
  • add a local LLM to System21
  • Infor System21 data access Db2 for i

Short answer

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.

Applies to: Infor System21 (formerly Geac System21) on IBM i; details differ by release, installed modules and customer modification.

Reference build for Infor System21

  1. 1Identify the System21 modules in use and the five questions users ask most.
  2. 2Trace each question to the Db2 for i tables behind the corresponding screens.
  3. 3Build read-only, business-named SQL views in a separate library and grant them to a service profile.
  4. 4Set up a replica or reuse an existing extract feed.
  5. 5Deploy an open-weight model on local GPUs with a tool server exposing parameterised queries.
  6. 6Carry over company and function security into the tool server filter.
  7. 7Pilot read-only first, log every query, review answers with the module owners.

Data access paths in Infor System21

System21 is a modular suite covering distribution, manufacturing and financials on IBM i. Its data lives in Db2 for i libraries, and the application is driven through its own menu and application management layer. Since exact file names differ by module and release, begin with the Db2 catalog (QSYS2.SYSTABLES, QSYS2.SYSCOLUMNS) and the product documentation for your installed modules, and write down the table behind each screen your users already trust.

Programmatic access is ordinary SQL through ODBC or JDBC, plus whatever interface programs and files your release documents for inbound transactions. We would not rely on an undocumented screen-scraping route. If your team already runs RPG or CL extracts to a reporting server, reuse that feed as the replica source, because it already encodes your business rules.

-- Which tables hold a given business column? Start from the catalog, not guesses.
SELECT TABLE_SCHEMA, TABLE_NAME, COLUMN_NAME, COLUMN_TEXT
FROM QSYS2.SYSCOLUMNS
WHERE COLUMN_TEXT LIKE '%CUSTOMER%'
ORDER BY TABLE_SCHEMA, TABLE_NAME;

-- Expose only an approved, named view to the assistant's service profile
GRANT SELECT ON AIREAD.OPEN_SALES_ORDERS TO AISVC;

Reference architecture, including the air-gapped option

A workable private AI layer for Infor System21 has six parts. First, a read-only data path: Db2 for i views over a replica or reporting copy so production is not queried. Second, a retrieval index over the documents and attachments people actually search, built with an open embedding model and stored in a vector database that runs on your servers. Third, a tool server, for example an MCP server, that exposes a short list of approved read actions with typed parameters. Fourth, an open-weight model served with vLLM or Ollama on local GPUs. Fifth, an identity layer that carries System21 identity, company and function into every request. Sixth, an audit log of who asked what, which queries ran and which documents were retrieved.

The model never receives a database connection string. It asks the tool server to run a named action, and the tool server builds the parameterised query, applies the user's visibility filter and returns rows. This keeps free-form SQL generation out of production paths and makes every answer traceable to a query you can show the user. For an air-gapped site, all six parts run with no outbound route; model weights and updates arrive on approved media and are scanned and checked before use.

Use a replica or scheduled extract so that assistant traffic does not compete with order entry and overnight batch. Many System21 sites already extract to a data warehouse; if so, that warehouse may be the cleanest source, provided it is refreshed often enough for the questions you want to answer.

Permissions: the assistant must never show more than the user may see

System21 security combines IBM i authority with application-level controls over who may run which functions and in which company or ledger. The assistant must not become a back door around that. Resolve each signed-in person to their System21 identity, determine the companies and functions they may use, and apply the same limits in the tool server before any query runs.

Where the Db2 version supports it, row and column access control can enforce company restrictions inside the database as a second layer behind the tool server.

Write-back only through supported interfaces

Keep the model out of System21 files. A user may ask the assistant to prepare an order note or a purchase request; the assistant writes a draft, the user reviews it, and a supported System21 entry function or interface posts it under that user's identity. The approval and result are logged.

Sizing, phased rollout and honest limits

Sizing depends on concurrency, not on headcount. A pilot of 10 to 20 users with a 7B to 14B class model can run on one workstation-class or datacentre GPU with 24 to 48 GB of memory. A site with 100 to 300 named users, of whom a third use it daily, often needs one to four GPUs depending on model size and answer length. Retrieval indexes for tens of thousands of documents are typically in the single to low double digit gigabytes. Use the sizing calculator for your own numbers and treat results as ranges.

Roll out in three phases. Phase one is read-only questions over a small set of views and documents, with every answer showing the query or sources. Phase two adds drafts, such as a summary, a message or a prepared transaction, that the user reviews but that nothing posts. Phase three adds approved actions through Infor System21's supported interfaces, always under the approving user's identity, with an audit record.

Because we cannot assume a single standard schema across System21 releases, expect to build the view layer per customer. That is real work and is where most of the quality comes from.

If staff only need fixed inquiries, the built-in enquiries and reporting tools are enough. A language model is worth adding for cross-module questions and for document search, not for lookups that a menu option already answers.

Try it here, free

Infor System21 Private AI Layer Blueprint Generator

Open full tool

Fill in your Infor System21 version, database, hosting and use cases and get a shareable architecture plan for a private AI layer.

Common pitfalls

  • !Guessing table meanings instead of tracing them from the screens users trust.
  • !Giving the service profile access to whole libraries rather than named views.
  • !Ignoring company and ledger separation in multi-company installs.
  • !Using a stale warehouse extract for questions that need today's stock position.
  • !Skipping module owners in answer review, so wrong business definitions go unnoticed.

How an ERP-grounded AI assistant handles this

ERPray and Netray's custom build work follow this pattern: read-only by default, the query is shown to the user, Infor System21 roles and visibility are respected, and everything runs on your hardware with open-weight models. Where a vendor's own AI or standard reporting already answers the question, we say so; the private layer earns its place for cross-system questions, document search and sites that cannot send data off premises.

See ERPray

Frequently asked questions

Is there an official System21 API for this?

Releases document interface programs and files for inbound data, but we would not assume one universal read API. For reads, SQL against Db2 for i through views is the most predictable route. Check your release documentation for supported inbound routes.

Can we reuse our existing data warehouse?

Often yes. If it is refreshed frequently and keeps the keys and codes users expect, it can serve as the replica. Check freshness against the questions you want to answer.

How do we avoid exposing other companies' data?

Resolve the user's companies from System21 and add that filter in the tool server for every query, with database row access control as a second layer where available.

Does it need a GPU?

For a pilot with a handful of users a single modern GPU can be enough. Use the sizing calculator for your user counts.

Related

Advanced

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

Infor XA keeps its data in Db2 for i on IBM i, so the safest way to add AI is a read-only reporting copy or logical-file access over JDBC or ODBC, a retrieval index over documents, a small tool server that exposes approved queries, and an open-weight model served on local GPUs. Nothing has to leave the building, and any write-back goes through the supported XA transaction programs after a person approves it.

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.

CIO briefing

Staffing an ERP AI Team: What Roles You Actually Need

Most mid-market organizations do not need a dedicated ERP AI team at pilot stage - one ERP-literate technical owner working part-time with an implementation partner is enough. A dedicated team becomes worthwhile once you have more than two or three live AI use cases in production, at which point you need a named owner for prompt/data quality, one for integration and access, and a business-side owner for adoption.

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.

Advanced

How to Add a Private AI Layer to PeopleSoft On-Prem

Reach PeopleSoft through its own mechanisms: PS Query exposed through Query Access Services, Integration Broker service operations, and Component Interfaces for writes. For bulk reads use a replica with the security join tables applied. Add a local retrieval index over file attachments and an open-weight model on your own GPUs, and keep row security equal to what the user sees in the application.

Advanced

How to Add a Private AI Layer to Hyperion and Essbase On-Prem

Essbase is a multidimensional cube, so the AI layer should call approved, parameterised MDX or report tools rather than letting a model write free queries. Authenticate as the end user so Shared Services provisioning and Essbase filters apply, pull narrative context from planning documents and commentary into a local index, and run the model on your own GPUs. Writes to plans stay in Planning forms, with human approval.

AI for ERP

AI for Infor System21: Grounded Answers on Top of IBM i

Add grounded AI to Infor System21: natural-language answers over distribution and manufacturing data, agents for order and inventory status, on-prem AI.

Stuck on Infor System21 (IBM i)?

Talk to engineers who work inside Infor System21 (IBM i) 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