Note
Accessing AI features: To use the AI features in Xentral, you must be enabled for the beta phase.
Prerequisite: Your instance is activated for AI features and you have access to the new features. If this is not yet the case, contact us at: support@xentral.com
In this article:
Here is where you can find the AI features and how to open them.
Steps:
-
Log in to your Xentral instance.
-
In the main menu on the left side, you will find a new AI icon that you can use to open the AI Agents menu item. Optional: On the home screen you will see an initial AI information tile as an introduction to the new features (dashboard tile).
-
In addition, you will find another AI icon (Co-Pilot) in the top right next to your profile. Click on this icon to open the AI Chat as a sidebar and work directly with the Co-Pilot (Chat).
Tip
Use the AI Chat when you want to actively ask questions about your business, get analyses, or trigger tasks directly in the ERP.
With the AI Co-Pilot you can quickly retrieve information, create analyses, and execute tasks directly.
Steps:
-
Open the AI Chat (Co-Pilot) via the corresponding menu icon.
-
Click on the chat input field "Message or command…".
-
Formulate your request as specifically as possible, for example:
-
"Give me an overview of my revenue for the last 14 days"
-
"Create a briefing for customer [Name]"
-
"Create an order for customer [Name] with item X"
-
Analyses and summaries are displayed directly. Suggestions for next steps or actions are highlighted. An action for your customer is created as a task, like an incoming email.
Start with simple questions or clear tasks. The more specific your request, the more precisely the Co-Pilot can help you.
You can also copy existing content (for example emails or requests) directly into the chat to have tasks or analyses created from them.
Tip
Use the email agents when incoming customer inquiries should be automatically analyzed, structured, and prepared for your processing.
Tip
How response suggestions and recommendations are generated
For each inquiry, you automatically receive a response suggestion and a recommended action. These are based on three central sources:
-
the specific inquiry from your customer
-
the available data in Xentral (for example orders, customers, status)
-
your stored company guidelines from the knowledge base
From this, the AI creates a confidence score evaluation, a suitable response template, and a concrete recommendation for further action.
Steps:
-
Click on Inbox at the top.
-
Send a customer inquiry to the email address provided for your instance.
-
The email is automatically created as a task in the system.
-
Wait briefly until the inquiry has been processed, and check: which agent has taken over the inquiry, what summary was created, what recommended action is suggested.
-
You also receive a response suggestion for each inquiry. You can send this to the customer or edit it — alternatively, you can also mark the inquiry as done.
When an inquiry is being processed by an agent, it is displayed to you in the queue.
Examples: Delivery of a defective item — customer sends photo and returns the item.
With the Learning Loop and the knowledge base, you train your AI agents and continuously improve their responses.
-
Open the Learning Loop menu item in Xentral.
-
Get an overview of your existing knowledge base.
-
Click on Edit to adjust an existing entry or + New entry to add new knowledge.
-
Select the appropriate type:
-
Company for general information (for example communication style, processes)
-
Specialist knowledge for product information, FAQs, or specific answers
-
-
Formulate your knowledge building block as a clear question-answer pair or instruction.
-
Save the entry so your agents can use it immediately.
Hinweis
Here are specific examples of company knowledge that is useful in the Learning Loop:
Communication style:
-
"We always address customers informally."
-
"Responses should be friendly, brief, and solution-oriented."
-
"No emojis in a B2B context."
-
"Always start with empathy when handling complaints."
Company context:
-
"We are a D2C e-commerce company for furniture."
-
"Our main markets are Germany and Austria."
-
"Shipping is exclusively with DHL and DPD."
-
"Our brands are called [Brand1], [Brand2], [Brand3]"
-
"Our websites are [www.ourcompanyexample.com] and [www.ourcompanyexample2.com]"
Special rules & exceptions:
-
"No refunds for individually manufactured products"
-
"Goodwill decisions only for regular customers"
-
"Follow up proactively if tracking is missing after 3 days"
Note
The current Xentral AI roadmap and planned AI features can be found here: Xentral AI Roadmap →
Tip
Actively shape the AI future of Xentral!
We don’t just want to fill Xentral with features — we want to develop exactly the intelligent solutions that save you real time in your daily work.
Do you have processes that frustrate you every day? Are there data volumes that are barely manageable manually? Share your vision with us! The more detail you provide about your use cases, the better we can understand how AI needs to work for you.
The AI agents support you in automatically understanding, preparing, and processing incoming tasks — particularly customer inquiries.
They:
-
analyze content (for example emails)
-
recognize the concern (for example return, delivery status, product question)
-
access your ERP data and your stored knowledge
-
create a summary, a response suggestion, and a recommended action
You no longer have to manually gather information — you review and decide.
This is one of the most important distinctions:
AI Chat (Co-Pilot) → When you actively want to know or trigger something
Use the chat for:
-
questions about your business (for example revenue, customers, inventory)
-
analyses and evaluations
-
briefings (for example for customers or processes)
-
manual actions (for example creating an order)
The chat is your analysis and control tool.
Email agents → When a customer inquiry comes in
Use agents for:
-
incoming customer emails
-
automatic classification (for example return, delivery status)
-
response suggestions
-
recommended actions
The agents work automatically in the background and take operational work off your plate.
Note: not all agents are available in the chat. However, you can always have a task created and route the inquiry to the inbox.
Typical reasons:
-
The information is not available in the ERP or is not clearly assigned
-
Context is missing in the request (for example time period, exact designation)
-
The Analytics module is missing for in-depth questions and KPIs
-
The use case is not yet fully covered (beta)
Important: The chat primarily accesses structured data and context.
Simply forward a customer inquiry to the provided email address (or set up automatic forwarding).
The process:
-
Email is created as a task
-
Inquiry is automatically classified
-
Matching agent takes over
You receive:
-
Summary
-
Response suggestion
-
Concrete next steps
Goal: Less manual processing, more focus on decisions.
The agents are based on three central sources:
-
your customer’s inquiry
-
your ERP data
-
your stored knowledge (Learning Loop)
In many cases, you will already receive very good suggestions. At the same time, during the beta phase:
Results should be reviewed before you adopt them.
Quality continuously improves through:
-
your feedback
-
your stored knowledge
-
real everyday usage
It can happen that an inquiry is assigned to the wrong agent — for example when a customer has sent multiple requests in one email, or it is not entirely clear which agent to assign the inquiry to.
In this case, you can:
-
manually review and correct the task
-
provide feedback
-
select a different agent and have the inquiry answered again
This feedback is central to improving routing and recognition.
For the AI to respond reliably and in your style, you should maintain at least the following content:
Company data & signature (for example sender, greeting formula) Website or relevant links Tone of voice (for example formal/informal, tone, example responses) Product information (ideally as FAQs) Rules & processes (for example returns, communication, special cases)
This is the most important foundation for good results.
No — but a few simple basic rules help enormously:
-
One task per request (don’t mix multiple topics)
-
Clearly state what you want
-
Provide context (for example customer, time period, goal)
-
Give examples if you expect a specific format
You don’t need technical knowledge — clear language is enough.
Your feedback plays a central role in the further development of AI features. Especially during the beta phase, we welcome specific feature requests and use cases from your everyday work. At the same time, the current version is deliberately focused on selected use cases. In the area of AI, much is possible — however, our customers differ greatly in business model, company size, and technical affinity. This results in very different requirements and expectations.
To set the right priorities, we use your feedback to better understand:
-
which features are most frequently needed
-
which use cases are relevant for different customer groups
-
where the greatest value is created
Based on this, we develop the AI features in a targeted way.
You can share your ideas and specific use cases with us at any time through the usual support or feedback channels.