Private AI for SAP Business One: Service Layer, a read replica and a local model
how to add AI to SAP Business One on-premise
Also searched as
- SAP Business One Service Layer AI assistant
- SAP Business One local LLM SQL Server
- SAP Business One chatbot without cloud
- SAP B1 HANA private AI
Short answer
Business One is small enough that a private AI layer can be simple: read through the Service Layer for live lookups, use a read replica of the SQL Server or HANA company database for analytics, index attachments and SOPs, and run an open-weight model on one or two local GPUs. Writes go through the Service Layer with a human approving first, never straight into the database.
Applies to: SAP Business One 9.3 and 10.0 on SQL Server or SAP HANA, on-premise or in your own hosting. Service Layer availability depends on version and database, so check the release notes for your patch level.
Build the layer on SAP Business One
- 1Confirm your version, database and whether Service Layer is installed and reachable (the /b1s/v1 endpoint). Note the session timeout and per-company configuration; the Service Layer login takes CompanyDB, UserName and Password.
- 2Create a read-only reporting path: a SQL Server readable secondary, log-shipped copy or HANA system replication target for analytical queries, so heavy questions never hit the live company database.
- 3Create dedicated B1 users for the AI layer with the minimum general authorizations, and decide whether queries run as that user plus an application-level filter, or as the asker through their own Service Layer session.
- 4List the objects you want to expose: sales orders (ORDR/RDR1), purchase orders (OPOR/POR1), items and stock (OITM, OITW), business partners (OCRD), production orders (OWOR/WOR1), journal entries (OJDT/JDT1).
- 5Index attachments and external documents: B1 stores attachment records (table ATC1/OATC) pointing to files in the attachments folder, plus SOPs, drawings and certificates on file shares.
- 6Wrap approved queries as named tools in an MCP or internal tool server, and serve the model with Ollama or vLLM on a local GPU.
- 7Add an approval queue for drafted documents, then post through the Service Layer. Log all calls and review the first weeks of questions with the users.
How Business One exposes its data
Business One has three integration surfaces. The Service Layer is a REST and OData service (path /b1s/v1, with a v2 on recent builds) that sits on the same business logic as the client, so business rules and validations run on writes. The DI API is the older COM interface used by add-ons and still behind many integrations. And the database itself, which is readable with SQL but not a supported write path.
The schema uses compact table names. Sales documents are ORDR (header) with RDR1 (rows); purchase orders OPOR with POR1; deliveries ODLN with DLN1; invoices OINV with INV1; items OITM, with warehouse stock in OITW; business partners OCRD; production orders OWOR with WOR1; journal entries OJDT with JDT1. Line status is 'O' for open and 'C' for closed. Always read the document structure for your version in the SDK help rather than trusting memory for less common columns.
For AI, use the Service Layer for single-document lookups and small lists, and the replica with SQL for aggregates. Service Layer queries support $filter, $select, $top and paging; use server-side paging so large lists do not time out.
-- Open sales order lines (SQL Server or HANA, run on the replica) SELECT T0.DocNum, T0.CardCode, T0.CardName, T1.ItemCode, T1.OpenQty, T1.ShipDate FROM ORDR T0 JOIN RDR1 T1 ON T1.DocEntry = T0.DocEntry WHERE T0.DocStatus = 'O' AND T1.LineStatus = 'O' ORDER BY T1.ShipDate;
# Service Layer lookup (after POST /b1s/v1/Login with CompanyDB, UserName, Password)
GET /b1s/v1/Orders?$select=DocEntry,DocNum,CardCode,DocTotal,DocumentStatus
&$filter=DocumentStatus eq 'bost_Open'&$top=50
Prefer: odata.maxpagesize=50Reference architecture for a small server room
Most Business One sites have a handful of servers, so keep the design light. One application host runs the tool server, retrieval index and audit log. One GPU host (a single workstation-class or data-centre card for a small user base) serves the model. A readable copy of the company database serves analytics, refreshed by log shipping, replication or a nightly restore depending on how fresh answers must be.
A request flows from the chat UI to an orchestrator that selects a tool, for example stock_by_warehouse or open_orders_by_customer. The tool runs a parameterised SQL query on the replica or a Service Layer call, returns rows with document numbers, and the model summarises with citations. No data leaves your network, and for an air-gapped shop the model weights are imported on removable media.
Because Business One deployments often serve several company databases, make CompanyDB an explicit tool parameter bound to the user's allowed companies rather than something the model can choose.
B1 company DB (SQL Server / HANA) --replica--> read-only copy --> tool server (parameterised SQL) B1 Service Layer (/b1s/v1) -------------------> tool server (live lookups) Attachments folder + file shares -> parser -> retrieval index Chat UI -> orchestrator -> Ollama/vLLM (local GPU) -> tool server -> cited answer Audit log: user, company, tool, parameters, document numbers returned
Permissions, data ownership and write-back
Business One authorizations are set per user in the general authorizations window, and Data Ownership lets you restrict who sees which documents (by owner, department, branch or sales employee) when enabled. Direct SQL on the replica ignores all of this, so you must reproduce it: export each user's authorizations and ownership scope and apply them as mandatory filters in the tool code, or make Service Layer calls under the asker's own session so B1 enforces it.
For many small deployments, the simplest honest model is: broad analytics tools only for roles allowed to see all data, and per-user Service Layer sessions for everyone else. Document which tools are available to which roles and review that list with the business owner.
Writes use the Service Layer so validations, posting rules and approval procedures run. The assistant drafts a document, a person reviews the exact payload, and an approved POST creates it, for example a draft sales order or purchase request. Use documents saved as drafts where the object supports them, so a person can finish them in the client. Never update tables directly; B1's own integrity and the SAP support terms depend on that.
Sizing, rollout and limits
As ranges: for 10 to 60 named users, a 7B to 14B open-weight model on one 24 to 48 GB GPU is often enough for Q and A over structured data, and a 30B-class model on one 80 GB card handles more complex document reasoning. The document index for a few tens of thousands of attachments is usually single-digit to tens of gigabytes.
Phase one: read-only questions on stock, orders, customers and open items. Phase two: drafted emails, quotation text and supplier follow-ups. Phase three: approved document creation through the Service Layer.
Limits. Business One has user-defined fields and tables (U_ and @ prefixed) that are different in every company, so mapping them is real work. Version differences matter: confirm which Service Layer features your patch level has. If your needs are mostly standard reports, B1's own query manager, Crystal reports and dashboards may already be enough, and an AI layer adds value mainly for questions that cross documents, notes and attachments.
Try it here, free
SAP B1 Service Layer Sales Order JSON Generator
Fill in server, company database, customer and line details to get ready-to-test Login and sales order POST requests for the Service Layer REST API.
Common pitfalls
- !Running analytical SQL on the live company database during business hours and slowing every user.
- !Ignoring Data Ownership and authorization settings when reading through SQL, so the assistant shows documents a user cannot open in B1.
- !Letting the model pick the CompanyDB freely in a multi-company install.
- !Writing to tables directly instead of the Service Layer, which skips validations and risks support issues.
- !Overlooking user-defined fields (U_ columns) so answers miss data the business treats as essential.
- !Hitting Service Layer session timeouts without a re-login and retry path.
How an ERP-grounded AI assistant handles this
ERPray can connect to Business One over the Service Layer and a replica, show the SQL or request behind each answer, and run entirely on a local server. For small teams the usual start is stock, open orders and customer history with a handful of SOPs indexed, then drafted documents with approval.
Frequently asked questions
Is the Service Layer or SQL better for an AI assistant?
Use both for different jobs. The Service Layer suits single-document lookups and writes because business rules run. SQL on a read replica suits aggregates and cross-table analytics. Keep SQL read-only, parameterised and on the replica, and never write through it.
Can we run this on a single server?
For a small pilot, yes: a modest GPU host plus an application host, or both roles on one machine, is workable. For production, separate the model host from the ERP database so inference load never competes with posting and reporting.
How do we handle Business One user permissions?
Either call the Service Layer under the asker's own session so B1 enforces authorizations and data ownership, or export those rules and apply them as mandatory filters in your SQL tools. Test with restricted users and log every query.
Does this work with SAP Business One on HANA?
Yes. The object names are the same, and you can read from a system replication target or a copy of the company schema. Service Layer is available on HANA, and the model and retrieval parts are independent of the database.
Related
Fix SAP Business One Service Layer 'Invalid session' (code 301)
The Service Layer returns code 301 'Invalid session or session already timed out' when the B1SESSION cookie you send no longer maps to a live session. The usual causes are the default idle timeout (30 minutes), a missing or altered cookie, a load balancer sending the call to a different node because ROUTEID was dropped, or a restarted Service Layer. Fix it by keeping cookies on every call and re-logging in once on a 301.
How-toSAP Business One Query: Released Production Orders with Component Shortages
Join OWOR (production order header), WOR1 (components) and OITW (stock per warehouse) to see, for every released production order, how much of each component is still to be issued and whether the warehouse can cover it. Run it in Tools > Queries > Query Manager, using double-quoted identifiers on HANA and the same query with minor syntax changes on SQL Server.
How-toSAP Business One MRP Wizard Returns No Recommendations: Checklist
When the MRP Wizard in SAP Business One produces an empty recommendation report, the cause is almost always data, not a bug: the item has Planning Method set to None, the scenario excludes the demand documents, the planning horizon is too short, or existing stock and orders already cover demand. Work through item planning data first, then the scenario, then the document selection.
Error fixSAP Business One: Posting Date Blocked by a Locked Period
When SAP Business One reports that the posting date deviates from the permissible range, the date falls in a posting period that is locked or in a sub-period that does not allow that type of posting. Check Administration > System Initialization > Posting Periods, confirm the period status and sub-period, and have an authorized user change it, or move the document to a date in an open period.
Error fixSAP M7 021: Deficit of SL Stock Quantity
M7 021 fires during a goods issue, delivery, or confirmation when SAP checks the unrestricted-use (SL) stock for the exact plant, storage location and batch combination and finds less than what you are trying to post out. Fix the entry (batch, storage location, quantity) first; only enable negative stock or downgrade the message to a warning if the business genuinely needs to post ahead of a receipt.
Error fixSAP IDoc Status 51: Application Document Not Posted
Status 51 tells you the IDoc reached the application layer and failed to post, but the status text itself is not the error - the real cause sits in the status record's long text or the linked application log. Fix the underlying data or configuration, then reprocess the IDoc through BD87 rather than editing the status.
AI for ERPAI for SAP Business One, Without Sending Your Books to a Public API
Add AI to SAP Business One without sending customer data or financials to a public API. Service Layer and DI API integration, sized for an SMB budget.
AI for ERPSAP AI Consulting for On-Prem and Private Deployments
What to demand from an SAP AI consulting partner when data must stay on-prem or private: OData/BAPI mechanics, Joule vs. private LLM, and buyer questions.
Stuck on SAP Business One?
Talk to engineers who work inside SAP Business One every week, and who build private AI that answers these questions from your own ERP data.
Keep exploring
Free tools
- SAP B1 Service Layer Sales Order JSON GeneratorFill in server, company database, customer and line details to get ready-to-test Login and sales order POST requests for the Service Layer REST API.
- SAP Business One Service Layer Request BuilderFill in host, company and item details and get ready-to-paste Service Layer requests for login, item query, sales order and production order.
- SAP Business One 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 Business One, with components, security controls and a three-phase rollout.
ERP fixes and how-tos
- SAP Business One integration: Integration Framework (B1i), Service Layer, DI API and connectorsSAP Business One integration options compared: Integration Framework (B1i), Service Layer, DI API and SaaS connectors, and when to use each.
- SAP Business One Query: Released Production Orders with Component ShortagesReady-to-run SAP Business One queries on OWOR, WOR1 and OITW to list released production orders with missing components, for SQL Server and HANA.
- What is the latest version of SAP Business One, and how to plan an upgradeHow SAP Business One is versioned (10.0 plus quarterly feature packages), how to find the current one, and a practical upgrade checklist for on-prem setups.
Runs with your ERP
- SAP Field Service Management with SAP Business OneHow SAP Field Service Management, with Coresuite, syncs with SAP Business One service calls and billing: data flows, setup, pitfalls and a private AI layer.
- ECOSIRE CPQ Configurator with SAP Business One: guided quotingHow the ECOSIRE CPQ configurator uses option models, requires/excludes rules and live cost roll-up to create SAP Business One quotes and orders.
- Ecosire quality control and inspection with SAP Business One: CoA, NCR and CAPAHow Ecosire's quality add-on for SAP Business One handles inspections, certificates of analysis, NCR and CAPA ageing and supplier quality reporting.
AI on your ERP
- AI for SAP Business One, Without Sending Your Books to a Public APIAdd AI to SAP Business One without sending customer data or financials to a public API. Service Layer and DI API integration, sized for an SMB budget.
- AI for SAP Business One Purchasing, From Purchase Request to A/P InvoiceGround AI in SAP Business One purchasing: purchase requests, POs, goods receipts and A/P invoices via Service Layer, read-only, on-prem or private cloud.
Integrations
- How to connect Power BI to SAP Business OneConnect Power BI to SAP Business One: SQL Server or HANA direct, Service Layer OData, gateway setup, key manufacturing dashboards and natural-language Q&A.
- How to add an AI chatbot to SAP Business OneAdd an AI chatbot to SAP Business One for staff or customers: grounded in Service Layer data, role-aware, with an on-prem open-model option.