xSuite powered by AI Agents:
The Game Changer in Accounts Payable

We combine cutting-edge AI technologies with our proven process and SAP expertise. Our goal is ambitious:

100% Touchless Invoice Management

With xSuite, formerly manual process steps are gradually taken over by specialized AI agents.
They improve quality, increase the touchless rate of already automated processes, and simplify workflows that are not yet fully automatable. 
The goal: Invoice management as close to 100% touchless as possible. 

Document Capture Revolutionized

xSuite uses deep learning and large language models (LLMs) for document capture.
This drastically reduces error rates, significantly improves recognition accuracy, and makes manual validation largely unnecessary.
As a result, capture truly becomes a driver of automation. 


Meet the xSuite AI Agents:

Matching Agent

  • Starts with the extraction of invoice data 
  • Automatically enriches and matches data with SAP master data 
  • Performs document reading down to line-item level 

Goal: Manual validation of capture results becomes the exception rather than the rule – the majority of invoices are processed touchlessly in the background. 

Verification Agent

  • Takes over after the Matching Agent 
  • Checks whether full background posting is already possible (e.g., in a 3-way match scenario) 
  • Automatically initiates the necessary steps when background posting is not yet possible (e.g., automatically waits for goods receipt) 

Goal: To largely automate the verification process and relieve AP staff from repetitive tasks. 

Workflow Agent

  • Takes over after the Verification Agent 
  • Checks whether touchless background processing is now possible 
  • Automates subsequent tasks as much as possible, e.g., by suggesting responsible approvers or account assignments 
  • Once all steps are completed, the document is automatically forwarded for posting and payment

Goal: Manage process handovers and approvals with maximum automation. 

Intelligent Combination of Logic and AI

The xSuite Agents don’t rely solely on AI — they are built on a smart combination of proven business logic and artificial intelligence. First, the AI captures and enriches as much information as possible. Then, programmed rules specifically check the AI’s results for plausibility.  
The result: a robust and reliable system. 

More Than Just Automation

  • xSuite Capture: Deep Learning and Large Language Models (LLMs) for modern document reading. 
  • xSuite Prediction Server: Deep-learning-based AI for SAP-integrated workflows. 
  • Dynamic Fraud Protection: Detects suspicious patterns based on historical transactions — before any damage occurs. 

AI Against the Skilled Labor Shortage

xSuite AI Agents take over recurring routine tasks. AP staff can focus on value-adding tasks — while AI takes care of repetitive work.

The Future of AP Automation Begins Now

With AI Agents from xSuite, you’ll get closer than ever to 100% touchless invoice management — faster, more precise, and more secure. 

Worth Knowing About Artificial Intelligence

Which AI technologies exactly are used in xSuite?

Various AI technologies are used in the xSuite solutions. The suggestion functions in the workflow (Prediction Server) are based on deep learning. Document reading is a mix: simple steps, such as self-learning supplier training, are based on machine learning. An R-CNN model (Region Based Convolutional Neural Network) is used for image recognition. It is also possible to use a large language model for document capture. 

What is the difference between “artificial intelligence”, “machine learning” and “deep learning”?

Artificial intelligence is the generic term for applications that demonstrate human-like intelligence and can solve problems. One sub-area of this is machine learning, in which algorithms learn from data to recognize patterns and make predictions without being explicitly programmed. Deep learning, on the other hand, is a specialized form of machine learning that is based on artificial neural networks with many layers and is particularly efficient with large amounts of data and complex tasks. While artificial intelligence encompasses many different methods, machine learning is a specific approach, and deep learning is the most advanced form of it.

What improvements in document capture can realistically be expected with the help of AI?

With the use of LLM models, significant improvements in document reading can be achieved in two areas. A central point is the recognition rates. An improvement from 85% to 95% recognition rate at field level is realistic. In addition, the effort required for a capture project is reduced by up to 80%.

Can I still review or correct the AI's entries?

Absolutely. The AI provides suggestions. When confidence is high, entries may be auto-filled – but a verification step always remains in place. AI is designed to assist, not replace, human oversight.

Knowledge & Resources on AI

How AI Is Transforming Accounts Payable

Read the blog article

Large-Language Models in Document Reading

Read the fact sheet

NOZ/mh:n boosts efficiency with xSuite AI

Read the case study

AI in Invoice Processing: What Can an LLM do?

Read the blog article

Get in Touch

Ask a question Request a quote Set up an introduction call

Stay informed –
Subscribe to the xSuite Newsletter.

Receive company and product news, exclusive invitations to events, and access to complementary webinars and training sessions.

Top