At first glance, order confirmations seem like a minor process. However, over the course of a year, they tie up many hours of operational capacity in procurement—time that is then missing for negotiations and supplier development. This webinar shows how a manufacturing company handed this verification process over to an AI agent and now processes four out of five order confirmations without any manual intervention.

Oliver Kosalla (Head of Procurement at Anton Debatin) and Denise Nöske (Operational Procurement at Anton Debatin) join Moritz Flick (Customer Development at Tacto) to discuss how they automated order confirmation verification using the Tacto AI agent, which steps made the difference, and which projects are coming next.

The Starting Point: When 2,700 order confirmations a year tie up 225 hours

‍

Anton Debatin is a family-owned company based in Bruchsal that manufactures flexible logistical packaging solutions made of polyethylene. Before the project, the procurement department handled around 2,700 order confirmations per year from approximately 330 active suppliers entirely manually. Each confirmation arrived via email, was compared against the purchase order for quantity, price, and delivery date, marked in the ERP system, and filed in the document management system.

With a verification time of three to eight minutes per transaction, this added up to more than 200 hours per year. On top of that, there were volatile prices and availability, increasing compliance requirements like the PPWR, and the realization that strategic procurement work was falling by the wayside. The speakers noted that a reliable, centralized database is a prerequisite, as automation only works with structured and accessible data.

‍

Document Understanding Instead of Masks: How the AI Agent Reads and Reconciles Order Confirmations

‍

Existing solutions quickly reach their limits. PDF extraction with OCR only maps items based on text, masks and templates must be created for every supplier and break with every format change, and image recognition requires large amounts of training data and, even with the best providers, achieves a maximum of 40 percent straight-through processing.

In contrast, the Tacto agent reads every format from every supplier on the first attempt, reconciles item numbers, quantities, prices, delivery dates, payment terms, and Incoterms at the line-item level with the order data from the ERP, and even recognizes handwritten changes on the confirmation. Discrepancies appear color-coded in the app, including an AI-generated suggestion for the email to the supplier. Debatin’s practical examples showed a price discrepancy from 32.13 euros to 31.13 euros per kilogram, where a discount was missing from the order, as well as a delivery date delayed by one day. Tolerances can be set down to the supplier level, and the system learns from every adjustment for all future confirmations.

‍

From Requirements Specification to Straight-Through Processing: Project Workflow and Results at Debatin

‍

Today, around 80 percent of order confirmation verification runs without manual intervention; only the approximately 20 percent with discrepancies go back to the procurement team. This frees up about 210 hours annually and, according to the business case, results in savings of approximately 12,600 euros per year for this process alone. More important than the numbers, according to the speakers, is the capacity gained for strategic topics in supplier management. Additionally, there is greater resilience during vacations and illness, as well as less waste because discrepancies are spotted early.

‍

Outlook: After Implementation Is Before Implementation

‍

The order confirmation verification was just the starting point for Debatin. Next, they are developing an automated supplier evaluation that combines data from supplier self-assessments in the Tacto SRM with delivery reliability and quality data from the ERP. The goal is to use it for upcoming annual reviews by the end of the year. In the fourth quarter, the team will also test an RFQ agent for daily inquiries in the trading goods sector, which currently cause a significant administrative burden. Invoice verification, which is still done entirely by hand, is also on the list.

‍

Conclusion

‍

The practical example from Anton Debatin demonstrates that operational routines in procurement can be gradually handed over to AI agents, even in medium-sized companies. The keys to success are a clean database, a clearly defined start with a few suppliers, and a team that helps shape the process from the beginning. The time saved is channeled into strategic tasks, and the first agent gradually evolves into a team of AI colleagues.

‍

Oliver Kosalla and Denise Nöske from Anton Debatin join Moritz Flick from Tacto to show how the verification of around 2,700 order confirmations per year now runs about 80 percent without manual intervention. The webinar explains how the AI agent detects discrepancies in price, quantity, and delivery date, how Debatin started the project with five suppliers, and which agents are coming next.