IBM i (AS/400) Custom RPG Applications Private AI Layer Blueprint Generator
This generator turns a handful of facts about your IBM i (AS/400) Custom RPG Applications environment into a structured architecture plan for a private AI assistant. It covers the components, the security controls tied to your hosting choice, a three-phase rollout and the questions IT has to answer before build.
Fill in
IBM i (AS/400) Custom RPG Applications Private AI Layer Blueprint Generator
Context
Company: Acme Precision Ltd System: IBM i (AS/400) Custom RPG Applications, version IBM i 7.4, database Db2 for i (native) Hosting: On-prem server Scale: 250 named users across 3 sites Target: Pilot in 8 weeks, production in 6 months
Goal: add a private AI assistant over the existing system without moving data to a public cloud service and without replacing the system.
Use cases in scope
Plain-language questions over order, inventory and customer files; explain what a batch job or RPG program does; summarize open orders and exceptions without green-screen navigation.
Data that must never leave the site
Customer financial data, pricing files, payroll libraries and any library outside the AI views. Column masks apply to sensitive fields.
Control: this data is excluded from the index or processed only on On-prem server infrastructure, with access logged.
Components
| Component | Design |
|---|---|
| Data access path | Read-only profile over JDBC (JTOpen) or ODBC to reviewed SQL views; stored procedures or IWS for logic in RPG; replica via journaling |
| Retrieval index | Field dictionary, spool files, manuals and program documentation indexed locally |
| Model serving | Open-weight model on vLLM or Ollama on 1 x 24 GB GPU, on a separate x86 server |
| Tool server | MCP or HTTP server with named view and procedure tools; EBCDIC and packed values converted |
| Identity and permissions | Per-role low-privilege profiles plus row and column access control on sensitive tables |
| Audit | Append-only log plus Db2 for i audit journal entries for the AI profiles |
Security controls
No direct file writes; write-back only through RPG programs via procedures with approval; AI profiles limited to AI-specific views; RCAC masks; analytical queries on a replica during batch windows.
Hosting mode On-prem server: when air-gapped, models, containers and packages enter through a hash-verified transfer and no component calls an external network.
Rollout
| Phase | Scope | Exit criteria |
|---|---|---|
| 1. Read-only questions | Cited answers over a pilot scope for a small user group on 1 x 24 GB GPU | Answers verified by process owners; no permission leaks in tests |
| 2. Drafts | Summaries, comparisons and drafted records a person reviews and enters | Reviewers accept drafts without major edits in agreed share of cases |
| 3. Approved actions | Narrow actions through the supported API with a named human approver | Every action logged; rollback path tested; sign-off from system owner |
Open questions for IT
1. Which libraries and files back the screens users ask about, and is there a data dictionary? 2. Which fields hold dates or codes as numeric or CHAR values? 3. What is the batch window, and can queries run on a replica? 4. Which logic exists only in RPG and must be called, not re-implemented? 5. Who still knows the application, and how long are they available?
Approvals
This is a planning document, not a security certification. Component choices (vector store, model size) depend on your pilot measurements; confirm API names and limits against the documentation for your exact version.
Review my blueprint
Send the exported plan for an optional review of the data access path, permissions design and rollout.
Optional. The tool and every export work without this. No spam.
How to use it
Enter your system version, database engine and hosting model, then describe the use cases and the data that must never leave the site. The blueprint fills the context, components, controls and rollout sections, and exports to PDF, Word or Excel. Walk through it with your IT architect and security officer, correct the defaults, and attach it to the project request. Change the GPU field to see how the rollout row for phase one reads on different hardware.
- Be specific about restricted data: it becomes a design constraint, not a footnote
- Pick hosting first; it sets the security controls
- Keep use cases to three or four for the pilot
- List the people who can approve write-back
What the blueprint assumes
The design is the same on every on-prem system: a read-only copy or supported API for data access, a retrieval index that carries permissions, a tool server that exposes only approved read actions, an open-weight model on vLLM or Ollama, and an audit log. The real cost is the semantic layer over short field names, not GPU hardware. The components table names the access path for this system, but you must verify the object and API names for your exact version.
- Read-only by default
- Permissions mirrored from the system
- Write-back only through supported APIs with human approval
- Everything logged
Reading the rollout table
Phase one proves the data and permissions work: cited answers over a small scope. Phase two adds drafts that a person reviews. Phase three allows narrow, approved actions through the system's own API. Do not skip phases: most failures come from skipping permission testing in phase one. Exit criteria are examples; replace them with numbers your process owners agree to, such as the share of answers verified correct in a sample of fifty questions.
Common mistakes
Teams often size the model before they have defined the use case, grant the assistant a powerful service account, or index everything to avoid deciding scope. Another is leaving the open questions unanswered until build starts. Small user base, high question rate. Use the open-questions section as the agenda for your first IT workshop and assign an owner to each item.
- Powerful service account for convenience
- No permission tests with restricted users
- Indexing without scope decisions
- No owner for open questions
Frequently Asked Questions
Does this document commit us to buying anything?
No. The generator runs in your browser and exports a plan you can share internally. It is a starting point for architecture and security review, and every default can be changed.
Is the plan valid for air-gapped sites?
Yes. Choose the air-gapped hosting option and the controls section adds transfer and network isolation rules. All components in the table run inside the closed network with no external calls.
Why does the plan avoid giving model sizes?
Model size and GPU count depend on concurrency, context length and answer quality targets. Measure them in the pilot, then use the sizing calculator for ranges rather than committing to a number early.
Can we reuse the plan for another system?
The structure transfers, but the data access path, permission model and open questions are specific to each system. Generate a separate blueprint for each platform and compare them.
Netray designs and runs private AI layers on IBM i (AS/400) Custom RPG Applications with your IT team. If you want a second opinion on your blueprint, we can review it with you.
Related Tools
IBM i (AS/400) Custom RPG Applications AI Assistant Sizing and Value Calculator
Estimate GPU count, token volume, index size and payback for a private AI assistant on IBM i RPG from users, usage and time saved.
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 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.
On-Prem AIRAG Infrastructure Sizing Calculator
Estimate vector storage, node RAM, generation GPUs, and monthly infrastructure cost for a retrieval-augmented generation deployment over your document corpus.
More On-Prem AI tools
See all- On-Prem LLM Total Cost of Ownership Calculator
- On-Prem vs Cloud AI Cost Comparison Calculator
- Self-Hosted LLM Hardware Estimator
- Air-Gapped AI Readiness Assessment
- LLM API vs Self-Hosted Cost Calculator
- Open-Weight Model Selector
- On-Prem AI ROI Calculator
- LLM Token Cost Calculator
- AI Data Center Power and Cooling Calculator
Keep exploring
Free tools
- IBM i (AS/400) Custom RPG Applications AI Assistant Sizing and Value CalculatorEstimate GPU count, token volume, index size and payback for a private AI assistant on IBM i RPG from users, usage and time saved.
- IBM Maximo Manage On-Prem Private AI Layer Blueprint GeneratorGenerate a shareable architecture plan for a private, on-prem AI assistant on IBM Maximo Manage On-Prem: components, security controls, 3-phase rollout and open questions for IT.
- SyteLine Private AI Layer Blueprint GeneratorFill in your SyteLine environment and get a ready-to-share architecture plan for a private, on-prem AI assistant.
ERP fixes and how-tos
- How to Add AI to an IBM i (AS/400) RPG Application Without Moving ItHow to add a private AI assistant to custom RPG applications on IBM i: Db2 for i access, field names, journals, RCAC security, local LLM, sizing and rollout.
- 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 REST API: expose XA through IBM i Integrated Web Services or IONHow to expose Infor XA (MAPICS) data and functions as REST on IBM i using Integrated Web Services or ION, with an example call and the safety rules for writes.