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 an AI icon that you can use to open the Agent Hub. You start on the Home page with your daily overview: pending items and your AI employees.
-
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 knowledge base, you train your AI agents and continuously improve their responses.
-
Open the Knowledge base tab in the Agent Hub.
-
Get an overview of your existing entries. Via the filters you can filter by type (for example Company, Specialist knowledge, Templates) and source (Manual, Website, Chat, File).
-
Click on the edit icon to adjust an existing entry, or on Add entry to add new knowledge. You have three options:
-
New entry – create a question-answer pair manually
-
Upload file – have knowledge extracted from a file (for example a PDF)
-
Import website – have knowledge extracted from a website
-
-
For manual entries, select the appropriate type:
-
Company for general information (for example communication style, processes)
-
Specialist knowledge for product information, FAQs, or specific answers
-
Templates for reusable response templates
-
-
Formulate your knowledge building block as a clear question-answer pair or instruction.
-
Save the entry so your agents can use it immediately.
In addition, entries are created automatically from your chats with the agents: When you correct an agent (for example "Max. 2% cash discount"), the system suggests saving this rule as a knowledge entry. You can recognize such entries by the source Chat.
Hinweis
Here are specific examples of company knowledge that is useful in the knowledge base:
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"
Have you already answered many similar customer questions by email over the past few months? You can reuse this knowledge directly for your agents – instead of creating every knowledge entry one by one via New entry.
This approach is a good fit if:
-
Email threads already exist: from your support or customer service inbox.
-
Fill the knowledge base in one go: instead of capturing question-answer pairs one at a time.
-
Reuse answers that already work well: instead of writing them again.
To do this, you export existing support emails, have an AI tool condense them into a question-and-answer table, and upload that table to the knowledge base in one step. A first run typically takes 10 to 15 minutes.
-
Export the relevant emails from your support inbox.
In your email inbox, filter for emails from the last 90 days in your support or customer service folder where customers asked you questions and you replied. The fastest way to capture several complete conversations at once depends on your email program:
-
Outlook (desktop, Windows): Select the relevant emails in the list and drag them into an empty Word document while holding down the mouse button. Outlook automatically inserts the subject, sender, and full text of each email. Save the document afterward.
-
Outlook on the web: Select the relevant emails, use the print function, and save the result as a PDF file.
-
Gmail: Save individual conversations as a PDF via the print function. For larger volumes, use Google Takeout instead and limit the selection to Mail and the relevant inbox label.
-
Smaller volume (up to about 20 conversations), regardless of email program: Open each conversation individually, copy the full text, and paste it into a shared document.
Tip
The more real conversations you collect, the better the result. Even 15 to 20 email threads are enough for a good first run.
-
-
Have an AI tool condense the emails into a question-and-answer table.
Open an AI tool such as Claude, ChatGPT, or Gemini and copy the following analysis prompt into the chat window. Immediately afterward, paste your collected email text or upload the saved PDF or Takeout file, then send the message.
You are analyzing a company's support email threads to build a knowledge base for an internal AI agent. Real email conversations between the company and its customers from the last 90 days follow this text. Your task: 1. Identify recurring or typical questions and the matching answers from the emails. 2. Summarize each question as a clear, generally understandable question. Summarize each answer as a clear, general answer that would also fit a new, similar case. 3. Important: Remove all personal and customer-specific data from the answers (names, company names, order numbers, email addresses, amounts, phone numbers). The answer should be generally valid, not tied to a specific individual case. 4. Only include questions that occurred multiple times or are clearly typical for the business. Leave out one-off special cases with no repeat value. 5. If an email is unclear, contradictory, or incomplete, do NOT include it instead of guessing. 6. Output the result exclusively as a Markdown table with exactly these three columns: Question | Answer | Source In the "Source" column, always enter "Email support". 7. No explanations before or after, only the table. Here are the email conversations: [PASTE THE EMAIL TEXT YOU COPIED IN STEP 1 HERE]
Important
Before sending, check whether the pasted email text contains sensitive data that should not be shared with an external AI tool, for example contracts, internal prices, or health data. The prompt only removes personal data from the result. The raw text you paste in still contains everything you copied into it.
-
Review the result.
You get back a table with the columns Question, Answer, and Source. Check whether the answers are still accurate, whether customer-specific data has really been removed, and whether an important, frequent question is missing. Add any missing questions manually and delete rows that don’t fit. No rewording is needed at this point.
-
Upload the reviewed table as knowledge.
Save the reviewed table as a file, for example as a text file or Word document. Open the Knowledge base tab in the Agent Hub and click on Add entry > Upload file. Select your saved file.
Your agents use the uploaded content for their responses immediately.
Tip
Repeat this process whenever new support emails have come in, for example every few months. This way, your agents' knowledge grows along with your day-to-day business, without you ever having to type out a single email by hand.
Note
The knowledge base is limited to 2,000 entries. Only upload recurring patterns, not every individual email.
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 (knowledge base)
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.