Infor XA private AI layer blueprint generator
This generator turns a few facts about your Infor XA installation into a structured architecture plan for a private AI layer. It is meant to give IT, the ERP owner and security a shared document to react to, not to replace design work.
Fill in
Infor XA Private AI Layer Blueprint Generator
Private AI layer architecture plan: Infor XA
Company: Acme Precision Ltd System: Infor XA XA 6.1 or earlier Database: Db2 for i (IBM i 7.3) Hosting: On-prem server Named users: 150 across 2 site(s) Target go-live: 2027-03-31
1. Context and goals
Acme Precision Ltd runs Infor XA (XA 6.1 or earlier) on Db2 for i (IBM i 7.3) and wants AI-assisted answers without moving data off its own infrastructure.
Primary use cases: Order status and shortage questions for customer service, item and BOM lookups for engineering, open PO and receipt questions for buyers, period-end variance explanations for finance.
The assistant is read-only in phase 1. Any write-back is prepared as a draft and posted only through Infor XA's supported interfaces after a named user approves it.
2. Components
| Component | Design | Notes |
|---|---|---|
| Data access path | JDBC/ODBC to read-only views over Db2 for i libraries, via a replica | Library list, journaling and dictionary |
| Change capture | Db2 journal receivers or scheduled extract | Journal sizing |
| Retrieval index | Vector index over documents and attachments with access-control metadata, on local storage | Chunking and refresh schedule to agree |
| Tool server | MCP or REST tool server exposing approved, parameterised read actions | Action list agreed with business owners |
| Model serving | Open-weight model on vLLM or Ollama; GPU: None yet | Model choice validated on Acme Precision Ltd questions |
| Identity and permissions | Read-only profile plus per-user XA company/facility filter | Profile mapping |
| Audit | Log of user, question, query or action, documents retrieved and answer | Retention set with compliance |
3. Security controls mapped to your inputs
Hosting model: On-prem server. If air-gapped, no outbound route exists for the model, index or tool server, and updates arrive on approved media after scanning.
Data that must never leave the site: Customer pricing, cost rolls, drawings and contract documents under ITAR or customer NDA.
Controls: read-only service account limited to named views, per-user visibility filters in the tool server, encryption at rest on the replica and index, network segmentation between the assistant and production, and an audit trail reviewed on a set schedule.
4. Rollout
| Phase | Scope | Exit criteria |
|---|---|---|
| 1. Read-only questions | Named views and a small document set for a pilot group; every answer shows its query or sources | Pilot users rate answers acceptable on agreed test questions |
| 2. Drafts | Assistant prepares summaries, messages or transaction drafts that are reviewed but not posted | Drafts accepted with few edits; no data exposure findings |
| 3. Approved actions | Posting through supported interfaces under the approving user's identity | Audit record complete; business owner sign-off |
5. Open questions for IT
1. Which libraries, schemas or organisations are in scope for 150 users at 2 site(s)? 2. Can a replica or reporting copy be provided, and with what refresh lag? 3. Which document stores need indexing, and what access rules apply to them? 4. Who owns the data dictionary and approves the action list? 5. What are the power, rack and cooling constraints for GPUs (None yet)? 6. How will model updates be brought in and approved?
Approvals
A planning aid, not a design guarantee. Verify table names, interfaces and supported versions against your Infor XA documentation and with your vendor or implementation partner before building.
Review of your Infor XA AI architecture
Optionally send your exported plan for a short expert review of the data path, permissions and sizing.
Optional. The tool and every export work without this. No spam.
How to use the generator
Fill in the company, version, database, hosting model, user count and sites. Write the use cases in plain language, for example the five questions users ask most often. List the data that must stay on site, such as pricing, controlled drawings or personal data. Then export the result to PDF or Word and circulate it. The open questions section is designed to start the right conversation with infrastructure and security teams.
- Be specific about use cases; vague goals produce vague scope.
- Name data classes, not just systems.
- Choose the hosting model honestly, including air-gapped if required.
- Share the export before buying GPUs.
What the blueprint contains
The plan has a context section, a component table, security controls mapped to your answers, a three-phase rollout and a list of open questions. The components follow a common pattern: a read-only data path over a replica, a retrieval index, a tool server, a locally served open-weight model, identity mapping and an audit log. The details for Infor XA reflect how it stores data and handles access.
- Read-only first, drafts second, approved actions last.
- Per-user visibility enforced outside the model.
- Every answer traceable to a query or document.
- Air-gapped operation supported by design.
Reading the output
Treat each table row as a decision to confirm, not a fact. For example, the data access row names a mechanism; your team still has to verify the exact objects in your release. The rollout table gives exit criteria so that each phase has a clear stop or go decision. Pair this blueprint with the sizing calculator to estimate GPU count and the monthly value so that the business case and the architecture agree.
- Use the sizing calculator for GPUs and payback.
- Run security review on section 3 before pilot.
- Assign an owner to every open question.
Common mistakes
The most common mistake is starting with the model instead of the data path and permissions. A good model on top of an unfiltered database is a security incident waiting to happen. The second is skipping the data dictionary: coded table and field names need plain-language descriptions or answers will be unreliable. The third is allowing write access too early. Keep the first phase read-only and measure answer quality before adding drafts.
- Do not give the model a database connection.
- Do not skip replica isolation from production.
- Do not index documents without their access rights.
- Do not call it done without an audit log.
Frequently Asked Questions
Does this generator send my data anywhere?
No. The document is generated in your browser from the fields you enter. You choose whether to share the export with anyone, including us.
Is the blueprint specific to Infor XA?
The structure is common to any private AI layer, while the data access, change capture and permission rows reflect how Infor XA stores data and handles access. You should still verify object names and interfaces for your version.
Can I use it for an air-gapped site?
Yes. Select the air-gapped hosting option. The security section then states that no outbound route exists and that updates arrive on approved media.
Who should review the output?
At minimum the IT lead, the Infor XA owner and information security. The open questions list is written so each can take away items to answer.
If you would like help turning this plan into a working Infor XA assistant on your own hardware, Netray builds private, on-prem AI layers with partners who know the system.
Related Tools
Infor XA AI Assistant Sizing and Value Calculator
Size the GPUs and estimate the monthly value and payback of an on-prem AI assistant for Infor XA users.
On-Prem AIOn-Prem AI Deployment Checklist
A 30-point pre-deployment checklist covering use cases, hardware, security, model operations, and rollout for self-hosted enterprise LLMs.
On-Prem AIOn-Prem AI Security Hardening Checklist
A practical control checklist for securing self-hosted language models, covering model provenance, network isolation, data governance, host hardening, and audit readiness.
On-Prem AIGPU Sizing Calculator for LLM Inference
Work out how many GPUs you need to serve a given open-weight model to your user base, based on memory footprint and token throughput.
More Other ERPs tools
See all- Infor VISUAL Work Order Status and Structure Reference
- Infor VISUAL Manufacturing Scheduling Checklist
- Infor XA (MAPICS) Period End Close Checklist
- Infor VISUAL Database Table Reference
- Infor XA (MAPICS) Application Module Reference
- IBM i Commands for Infor XA Administrators Reference
- Acumatica Generic Inquiry Design Template
- Acumatica Manufacturing Edition Setup Checklist
- Sage X3 Import Template Worksheet
Go Deeper
On-Prem LLM Deployment Architecture: Reference Guide
Reference architecture for on-prem LLM deployment: inference servers, GPU sizing, RAG pipelines, and security zones for regulated manufacturers.
Security Hardening for On-Prem AI Stacks
Security hardening for on-prem AI stacks: container isolation, model supply chain, prompt injection defenses, and audit logging for defense contractors.
Keep exploring
Free tools
- MAPICS and Infor XA Private AI Layer Blueprint GeneratorGenerate a shareable architecture plan for adding a private, on-prem AI assistant to MAPICS and Infor XA, with components, security controls and a three-phase rollout.
- Infor System21 Private AI Layer Blueprint GeneratorFill in your Infor System21 version, database, hosting and use cases and get a shareable architecture plan for a private AI layer.
- SAP S/4HANA On-Prem Private AI Layer Blueprint GeneratorFill in your version, database, hosting and use cases to get an architecture plan for adding a private, on-prem AI assistant to SAP S/4HANA, with components, security controls and a three-phase rollout.
ERP fixes and how-tos
- How to add a private AI layer to Infor XA on-premReference architecture to add AI to Infor XA on-prem: read-only data path, retrieval, permissions, local GPUs, write-back control and rollout.
- Infor XA Factory Track: What It Does and How to Plan Shop Floor Data CollectionWhat Factory Track does for Infor XA shop floor data collection, which transactions it captures, how to plan a setup, and alternatives when it is aging.
- Infor XA costing: cost types, roll-up and standard cost setupHow product costing works in Infor XA (MAPICS): standard versus current cost, how roll-up builds cost from BOM and routing, setup order, and common pitfalls.
Integrations
- How to add AI agents to Infor XA on IBM iHow to add AI agents to Infor XA on IBM i: a tool layer over Db2 for i and RPG programs, approval gates, on-prem models, and realistic expedite and exception flows.
- How to add an AI chatbot to Infor XAHow to add an AI chatbot to Infor XA on IBM i: grounded answers from Db2 for i, internal and customer portals, role-based access, and a fully on-prem option.