JobBOSS Classic Private AI Layer Blueprint Generator
This generator produces a structured architecture plan for adding a private AI assistant to JobBOSS Classic without moving data to a public cloud. It captures your version, database, hosting model, users and sensitive data, and returns a document you can send to IT and security. Export it as PDF or Word.
Fill in
JobBOSS Classic Private AI Layer Blueprint Generator
Private AI Layer Blueprint: JobBOSS Classic
Prepared for: Northfield Fabrication LLC
Scope: a private AI assistant for Not sure running on Microsoft SQL Server 2012 or 2014, hosted as: On-prem server. Named users: 45. Sites or plants: 1. Target go-live: Q1 2027 for read-only phase.
Principle: the assistant reads from a copy of the system, runs open-weight models on infrastructure the company controls, and changes data only through supported interfaces after a named person approves.
1. Context and use cases
Use cases in scope: Job and operation status, late jobs by work center, material on order, delivery date questions from the sales desk.
Data that must never leave the site: Labor rates, burden and margin, customer drawings, quotes and pricing.
Available GPU: None yet.
2. Components
| Component | Design for JobBOSS Classic | Notes |
|---|---|---|
| Data access path | Read-only SQL Server login on a restored or log-shipped copy; client or supported import for approved writes | Read-only account; no direct writes to application tables |
| Retrieval index | Local vector store over documents and long-text fields, tagged with customer, job and document class | Embedding model runs locally |
| Model serving | Open-weight model on vLLM or Ollama, GPU: None yet | Sized for 45 named users; see sizing calculator |
| Tool server | Approved parameterised read actions exposed through MCP or similar | Every call logged; limits on rows returned |
| Identity and permissions | JobBOSS user mapped to a role, with views scoped per role in the tool server | Scope applied to queries and retrieval filters |
| Audit | Append-only log of user, prompt, tool calls, rows returned and answer | Retained on site per company policy |
3. Security controls for Northfield Fabrication LLC
Hosting: On-prem server. All inference, embeddings and indexes stay inside this boundary.
Data that must not leave: Labor rates, burden and margin, customer drawings, quotes and pricing. This data is excluded from any external service, and outbound network access from the AI components is blocked or limited to an allow list.
Access: users sign in through the company identity provider; the assistant enforces the same data scope as the system for each user. Database credentials are held in a vault and the account is read-only.
Write-back: disabled in phases 1 and 2; in phase 3 only for named actions, through supported interfaces, with human approval showing the exact change.
4. Rollout phases
| Phase | Scope | Exit criteria |
|---|---|---|
| 1: Read-only questions | Status and lookup questions over the use cases above, with the query shown to the user | Accuracy measured on a test set agreed with power users; scope tests pass |
| 2: Documents and drafts | Document Q and A and drafted messages or transactions that a user enters manually | Citations verified; no cross-scope leakage in tests |
| 3: Approved actions | A short list of write actions through supported interfaces with approval | Each action signed off by the business owner and IT |
5. Open questions for IT
1. Which database edition, version and replication options are licensed for Microsoft SQL Server 2012 or 2014? 2. Who owns the read-only copy and its refresh schedule? 3. Which identity provider and groups map to roles for 45 users across 1 site(s)? 4. Where will the GPU host sit, and how are model files approved and updated? 5. What is the retention period for audit logs? 6. Which customer or regulatory commitments restrict where data may be processed?
This is a planning document, not a security certification or legal advice. Table and API details differ by release, so verify each data access detail against your own system before building.
Get this blueprint reviewed
Send the exported plan and a Netray engineer will review it against your JobBOSS Classic setup and flag gaps. Optional; the generator is free without it.
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 and site counts, and the use cases you want first. List the data that must never leave the site as specifically as you can, because the security section is built from it. Then export the document and use it as the agenda for a review with IT, security and the business owner.
- Start with two or three use cases, not ten
- Be specific about restricted data classes
- Pick the hosting model your policy allows
- Share the open questions with IT before the meeting
What the blueprint contains
The plan sets out the context, a component table (data access path, retrieval index, model serving, tool server, identity and audit), the security controls mapped to your inputs, a three-phase rollout and a list of open questions. The component choices follow a common pattern: read from a copy, retrieve documents locally, serve an open-weight model on your GPUs, and log everything.
- Data access path: Read-only SQL Server login on a restored or log-shipped copy; client or supported import for approved writes
- Identity: JobBOSS user mapped to a role, with views scoped per role in the tool server
- Phases: read-only, drafts, approved actions
Reading the output critically
Treat the blueprint as a starting hypothesis. Table names, interfaces and replication options vary by release, so have your administrator confirm each data access item. Check licensing for any database replication feature you plan to rely on, and decide who will own the model host, the index and the audit log after go-live.
Common mistakes
Teams often start by pointing the model at the production database, letting write-back arrive in the first release, or skipping role tests. Another frequent error is ignoring documents: much of the value is in drawings, certificates and procedures that never sat in the database.
- Production database used for AI queries
- No role or scope tests before go-live
- Write-back enabled too early
- No owner for the audit log
Frequently Asked Questions
Is this blueprint specific to JobBOSS Classic?
The data access path, identity mapping and component notes are tailored to JobBOSS Classic, but you should still verify table names, interfaces and licensing against your own release before building.
Does the plan require a public cloud?
No. The design keeps inference, embeddings, indexes and logs inside your boundary. You can choose on-prem server, private cloud or air-gapped hosting in the form.
Can I give the output to my security team?
Yes. It is formatted for sharing and lists controls and open questions. It is a planning document, not a certification, so your security team will still apply its own review.
Do I need a GPU before I start?
No. The form accepts none yet. The sizing calculator estimates GPU count from your usage, and a pilot can start on a single 24 GB or 48 GB GPU.
Netray builds read-only AI layers for shops still on classic JobBOSS. If you want this blueprint checked against your SQL Server schema and users, ask for an expert review.
Related Tools
JobBOSS Classic AI Assistant Sizing and Value Calculator
Estimate peak concurrency, GPU count, index size, hours saved and payback for a private AI assistant on JobBOSS Classic.
On-Prem AIPrivate AI Total Cost of Ownership Calculator
Model the full 3-year cost of an on-prem AI deployment, including amortized hardware, power, staff time, and support, against comparable API spend.
On-Prem AIQAD EE Private AI Layer Blueprint Generator
Fill in your version, database, hosting and use cases to get an architecture plan for a private, on-prem AI assistant on QAD EE, ready to share with IT and security.
More On-Prem AI tools
See all- On-Prem LLM Total Cost of Ownership Calculator
- GPU Sizing Calculator for LLM Inference
- 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
- RAG Infrastructure Sizing Calculator
- Open-Weight Model Selector
- On-Prem AI ROI Calculator
Keep exploring
Free tools
- JobBOSS Classic AI Assistant Sizing and Value CalculatorEstimate peak concurrency, GPU count, index size, hours saved and payback for a private AI assistant on JobBOSS Classic.
- E2 Shop System Private AI Layer Blueprint GeneratorFill in your version, database, hosting and use cases to get an architecture plan for a private, on-prem AI assistant on E2 Shop System, ready to share with IT and security.
- QAD EE Private AI Layer Blueprint GeneratorFill in your version, database, hosting and use cases to get an architecture plan for a private, on-prem AI assistant on QAD EE, ready to share with IT and security.
ERP fixes and how-tos
- How to Add a Private AI Layer to Classic JobBOSS On-PremHow to add a private on-prem AI assistant to classic JobBOSS: read-only SQL Server access, job and operation data, permissions, GPU sizing and rollout.
- JobBOSS 2 vs JobBOSS: Differences, Versions and How to UpdateJobBOSS2 versus classic JobBOSS: what changed, how to find your version, and how to update or upgrade an existing installation safely.
- JobBOSS Public API: What Integration Options Exist for JobBOSS and JobBOSS2What integration options JobBOSS and JobBOSS2 offer: direct SQL, import tools, SDK or API access and partner connectors, with ways to link CAD, quoting and accounting.
Integrations
- How to add AI agents to ECI JobBOSS2How to add AI agents to ECI JobBOSS2: a read-first tool layer over the SQL Server data and API, agents for quotes, late jobs and POs, with human approval on writes.
- How to add an AI chatbot to ECI JobBOSS2Add an AI chatbot to JobBOSS2 for staff and customers: grounded in job, PO and inventory data, role-aware, and able to run on-prem with open-weight models.