Production
Structured capture at the point of work.
Case Study | Forge AI for SAP Business One
The Challenge
Sachets, filling, blending, and bagging each ran on paper forms. Staff retyped every form into spreadsheets by hand, so a transposed batch number or a wrong quantity landed inside inventory and product cost. Harney wanted clearer data and faster decisions, with no new risk to the systems already running the business.
You should not have to trade control for speed to put AI to work.
The Approach
Most AI pilots stall after the first win. The next team needs clean shared data, written rules, and access controls the pilot never had to solve. Harney fixed each one on SAP Business One before adding the next workflow.
20+ paper forms across sachets, filling, blending, and bagging were retyped by hand into spreadsheets. Structured digital forms in Forge AI now validate every entry at the point of work, and a product information layer keeps item names, pack sizes, and specifications consistent. Clean records at the source, and one product record for every team.
A question spanning production and sales meant pulling exports and matching rows by hand, often for hours. Forge built a semantic layer, a shared map of what the data means, linking floor forms, purchase orders, and SAP Business One item codes across 100,000+ records. Leaders see production, procurement, and sales from one current picture.
As automation scaled, approvals, access, and business rules drifted out of step with the workflows they governed. Harney set read-only SAP Business One access by default, narrow permissions for every automation, and approval before any automation connects or acts. Nothing posts to SAP Business One until a person approves.
The supervisor who knows which customer rounds up. The planner who knows which supplier ships short. Each rule is now written once, in one place Forge follows every time, with working know-how captured straight from Slack. Every shift follows the same logic from day one.
The Result
Each new team started from the same trusted data and controls. Harney finished the first phase with a clear, priced plan for the next two automations, product data and order processing.
Structured capture at the point of work.
Purchase orders turned into sales orders, with approval before posting.
Product information management on one consistent record.
Shared data across sales, production, and procurement.
Your Next Step
Score yourself honestly. If two or more are missing, fix the foundation before you buy the next automation.
No retyping between the floor and the system.
The same item data on the floor, at the order desk, and in SAP Business One.
Records matched at scale, so one question gets one answer.
Scoped permissions for every automation.
Kept with each workflow, not in someone’s head.