Claims service with calm and pace: notifications on every channel, checks of invoices and policies with Semantic², agreements signed in the conversation and routine requests resolved in self-service.
Semantic² for claims documentsSignature in the conversationDORA documentsSelf-service for routine
A burst pipe on a Sunday evening. The customer reports it in the chat, uploads photos and wants to know what happens next. Univerx opens a case from it that stays the same across every channel.
When she calls on Monday, the service agent sees the notification, the photos and the status. Nobody asks twice. Call distribution takes her straight to the responsible team.
Service EN· active
Queues
Voice3 waiting
Chat5 waiting
Email2 waiting
Messaging1 waiting
Conversation
AI agent, disclosedHandover from AI agent · context complete
I received the decision letter, but the amount does not match my application.
I have the case in front of me. One moment, I am checking the calculation.
Sentiment: calmVoice
Context
Case
2026-0412
History
3 · 14 d
Univerx Assist
Suggested reply
The letter deviates from the application. I will propose a correction and send you the confirmation by message.
InsertAccept
Summary
Request: deviation in the letter. Documents on file. Next step: correction, confirmation by message.
A claim in the desktop: history from chat and phone, photos, policy and the next step in one place.
Almost every claim comes with documents: tradespeople's invoices, expert reports, estimates. Semantic² reads them, scanned ones included, and checks them against policy, tariff and amounts already booked.
The result is a finding in euros: amount, rule, location in the document. Items billed twice or deviating hourly rates become visible. The claims handler accepts or rejects the finding.
Invoice
Item 4 · deviating rate€184.50
FindingSample
€184.50
Rule
Rate × hours
Source
Invoice, line 4
Booking
Voucher 2026-0412
AcceptReject
A Semantic² finding: amount, rule and source. The decision stays with the claims handler.
Many claims end with an agreement. In the Univerx Channel the customer and the claims handler see the same document, settle open questions and close. eIDAS signatures are the goal; the result goes into the case.
Not every request needs a claims handler. Change of address, a confirmation of cover, a question about processing status: AI agents resolve these on the phone and in web messaging, around the clock.
The agent is disclosed as AI in the dialogue and acts only in approved systems. When things get sensitive, such as a complaint or a personal injury, it hands over to a person at once, with a summary and the case.
Optional add-ons that matter in this industry: built on the same platform and at home in the same case.
Add-on
Semantic²
Reads the documents behind every case. Findings in euros.
Invoice
Item 4 · deviating rate€184.50
FindingSample
€184.50
Rule
Rate × hours
Source
Invoice, line 4
Booking
Voucher 2026-0412
AcceptReject
Semantic² is an optional add-on to the Univerx platform. It reads the decision letters, contracts and invoices behind a case, checks them against rules and bookings and reports deviations as a finding in euros. The decision stays with people.
Every finding with a sourceAmount, rule, location in the document and booking sit side by side. Nothing has to be taken on trust.
Structured and scannedReads forms as well as scans and photos, marking the passage it read.
Rules you knowCheck rules are readable and versioned. What is checked can be explained.
People decideNo finding is booked automatically. Accepting or rejecting is an action with a log entry.
Add-on
Univerx Channel
Identity, signature and resolution in one contact.
Sign4 / 5
Online ID card✓ Identity confirmed
Shared view
SignatureSigned
An optional add-on to the Univerx platform: a link with no download opens a guided dialogue with a shared view. Identification with the online ID card and eIDAS signatures are the goal, and the result goes back into the case. One request, one contact.
A link, not an appNo download, no account: the Channel opens in the browser on phone or desktop.
Guided dialogueThe conversation follows the request, asks only what is missing and skips what does not apply.
Shared viewBoth sides see the same page or form, with video if wanted.
Upload documentsProofs are photographed or uploaded during the conversation and attached to the case.
Building blocks
The capabilities behind it.
These capabilities and add-ons carry the solution. Each one is described on its own – with flow, use and rules.
Univerx Contact Center
Task routing
Back-office tasks are distributed like contacts: applications, forms, follow-up questions and wrap-up work reach the right person by skill, deadline and priority, with workbins and follow-ups.
AI agents understand the request, act in connected systems and hand over to people with context. On the phone as a voicebot, in chat as a text agent, always disclosed as AI.
Asynchronous chat on your website and in your apps. Customers can pause and pick up later, the history is kept, and AI agents handle what they can resolve.
Transcripts, topics, sentiment, compliance cues and root causes from calls and messages. So you see why customers get in touch, not just how often. Configurable for co-determination.
Transparency, human oversight, fairness, privacy and governance for every AI module in Univerx: AI agents, Univerx Assist, conversation analytics, knowledge and Semantic². Principles that work as settings.
Steer back-office work the way you steer customer contacts: task routing with SLAs, workbins and tracking. Semantic² checks the documents and returns findings in euros with their source. A person always makes the decision.
Close cases that need an identity or a signature within one contact: a link with no download, identification with the online ID card and eIDAS signatures as a goal in the Univerx Channel, and the result straight back into the case.
AI agents resolve routine requests on the phone and in chat, at any hour. They are disclosed as AI, act only in approved systems and hand over with context as soon as a person is needed.
Every request on the right channel, with the right person, with the whole context. Routing, workspace, Univerx Assist and knowledge work together in one flow.
Rules & evidence
The regulations that apply here.
How Univerx meets the requirements is in the trust center – with a status per topic and documents on request.
DORA
Since January 2025, DORA has required banks, insurers and other financial entities to manage their ICT providers rigorously. Univerx is designed to supply the documents you need for that.
AI disclosure in dialogue, human oversight, logging and model approval: Univerx is designed for the duties of the AI Act. Which risk class your use case falls into, we work out together.
Processing under Art. 28 GDPR, documents for your data protection impact assessment, retention and deletion policies and role rights. What exists you receive on request; what is a goal we call a goal.
The Univerx Channel is designed for identification with the German online ID card and for eIDAS signatures – inside the running contact, with no app to download for the Channel. It is prepared for the EUDI wallet.
No. Semantic² reads documents, checks them against rules and policy and shows findings with their source. Accepting or rejecting is up to the claims handler, and every decision is logged.
How does Univerx reach our policy and claims systems?
Through connectors and open APIs. Your systems of record stay in the lead; Univerx reads context for the conversation and writes results back into the case.
Does AI in claims service fall under the EU AI Act?
That depends on the specific use. Univerx is designed for disclosure, human oversight and logging. Classify your case with your legal team; we supply the documents for it.
Do customers need an app to sign?
No. The Univerx Channel opens from a link in the browser. No download is needed.
Which documents suit it, which checks make sense and which decision stays with people: a guide to introducing Semantic², from the first rule set to a pilot with a single document type.
Disclosure, handover, permissions, logging, approval and measurement: what should be settled before an AI agent goes live in customer service – step by step, with a checklist for the project team.
