Skip to content
ContactRequest a demo

Use case

Self-service around the clock

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.

Request a demoFlow

Flow

From first contact to resolution.

The flow in a few steps. Every step runs on the same platform, without switching systems.

  • 01 · ContactThe customer calls or writes in the chat, at night and at weekends too. An AI agent takes the request and identifies itself as AI.
  • 02 · UnderstandThe agent recognises the request in natural language and only asks for what is really missing.
  • 03 · ActIt does what you have approved: check a status, book an appointment, change an address. Every action is logged.
  • 04 · Hand overIf a person is needed, the agent hands over with a summary. Outside service hours, a callback is arranged.
  • 05 · LearnConversation analytics shows where the agent helps and where it does not. Prompts and flows are adjusted and approved in Agent Studio.

What the platform adds

What carries this flow.

The qualities that count day to day – for customers as much as for the teams.

  • Disclosed as AI

    The agent says it is an AI, on the phone and in chat. Customers can ask for a person at any time.

  • Grounded answers

    Answers come from Univerx Knowledge, a maintained knowledge base. The agent does not invent rules or quote made-up prices.

  • Acting within limits

    The agent works only in connected, approved systems. You decide what it may do; every action is in the log.

  • Handover with context

    The service agent sees the summary, the recognised data and the steps so far. Nobody has to tell their story twice.

  • Phone and chat

    The same agent works as a voicebot on the phone and in web messaging. Flows are built once and used across channels.

  • Building without code

    Agents, prompts and flows are built in Agent Studio without programming. Approval and versioning included.

#Around the clock, without hold music

Many requests arrive when the service team is not there: evenings, weekends, public holidays. Others arrive in bursts, when everyone has the same question at the same time.

Self-service with AI agents absorbs both. The agent understands the request in natural language, acts in connected systems and hands over when a person is needed.

A grounded answer: the agent replies from Univerx Knowledge and cites the source.

#What a good AI agent does, and what it does not

It doesIt does not
Say that it is an AIPretend to be a person
Answer from the knowledge baseInvent rules or prices
Act in approved systemsChange what nobody approved
Hand over with a summaryLeave customers without a way out

You set the limits. In Agent Studio teams define which tools an agent may use, test new versions and approve them.

#On the phone: voicebots

On the phone the same agent works as a voicebot. It speaks in natural language instead of keypad menus. For simple requests, classic IVR remains an option too.

If the team is busy and the queue is long, the voicebot offers a callback. The customer does not have to stay on the line.

#Disclosure and oversight

The EU AI Regulation (Regulation (EU) 2024/1689) sets out transparency duties in Art. 50: people should know when they are interacting with an AI system. Univerx is designed for disclosure, human oversight and logging.

How this looks in the product is described in the Trust Center entry on the EU AI Act. The post Disclosing AI without breaking the conversation offers wording for everyday use.

#How to recognise success

Do not only count how many contacts the agent takes. What matters is how many requests it actually resolves, how often it hands over and whether customers call again shortly afterwards. Conversation analytics shows the topics behind it.

#What goes with it

When the agent hands over, customer service starts with full context. How to introduce AI agents step by step is described in the guide Introducing AI agents responsibly.

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 AI

    AI Agents

    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.

    Learn more
  • Univerx AI

    Voicebots

    AI agents on the phone: they understand natural speech, clarify the request, act in connected systems and hand over to people with context. Disclosed as AI, available around the clock.

    Learn more
  • Univerx Contact Center

    IVR & self-service

    Voice menus and speech dialogues resolve simple requests around the clock. Those who need a person arrive with context, and instead of hold music there is a callback on request.

    Learn more
  • Univerx AI

    Univerx Knowledge

    One knowledge base for employees, AI agents and self-service. With semantic search that understands what is meant, and generated answers that rest on your sources and name them.

    Learn more
  • Univerx AI

    Agent Studio

    The workbench for AI agents and prompts: build without code, test with real examples, approve through roles and version every change. Built once, usable in every channel.

    Learn more
  • Univerx AI

    Conversation Analytics

    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.

    Learn more

Industries

Where this flow often starts.

Industries in which this use case is often the first step – each with its own rules and add-ons.

  • High-voltage pylons in the morning haze

    Utilities & telecoms

    High volume, many routine requests: AI agents for meter readings, tariffs and bills, outage communication at peak times, payment reminders with consent checks. Documents for your NIS2 obligations on request.

    • AI agents for routine
    • Outage communication
  • A tree blown over onto a fence after a storm

    Insurance

    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 documents
    • Signature in the conversation
  • A lit boutique window in the evening

    Retail & e-commerce

    Order and returns service via messaging, chat and phone, proactive delivery notices, help in the shop at the right moment and accessible customer interfaces as a goal under the European Accessibility Act.

    • Messaging & web messaging
    • Proactive delivery notices
  • A hand on a laptop beside a stethoscope

    Healthcare

    Hospitals, practices, care services and pharmacies on one platform: appointment service with reminders and callbacks, video consultations in the browser, pre-sorting of requests and patient service on every channel. Designed for the protection of special categories of data.

    • Appointments without a phone queue
    • Video consultations without a download
  • Vaulted entrance hall of a historic building

    Public sector

    The complete platform for citizen service: every channel in one queue, public service numbers and hotlines with AI agents, appointment booking, video, secure messaging and translation. Plus the digital citizen office for a visit to the authority in one session. Designed for social data protection and accessibility.

    • Digital citizen office
    • Citizen service on every channel

Frequently asked questions

Does self-service replace our service team?

No. AI agents take on recurring requests so the team has time for advice, complaints and exceptions. Handover to a person is possible at any time.

What happens if the agent cannot answer a question?

It says so openly and hands over to a service agent, with a summary. Outside service hours it offers a callback.

How do you prevent invented answers?

Generated answers are tied to Univerx Knowledge. If the agent finds no grounded answer, it does not make one up; it hands over.

Which requests are suitable to start with?

Frequent, clearly bounded requests with an unambiguous outcome: status, appointment, address, certificate. A pilot begins with one of them.

Further reading

  • Hands typing on a keyboard in the dark
    Guides2 November 2026 · 11 min read

    Introducing AI agents responsibly

    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.

  • A laptop under a desk lamp in a dark room
    Guides2 November 2026 · 11 min read

    Knowledge management for customer service

    Building one knowledge base for people, bots and self-service: what belongs in it, how articles are structured and written, how grounded answers come about, who maintains and approves, and how to tell whether the knowledge holds up.

  • Employee wearing a headset at a screen
    AI in customer service30 October 2026 · 5 min read

    Why the handover decides: AI agents and context

    The most delicate moment in an automated conversation is not the hard question. It is the switch to a human. Plan it, and neither side has to repeat itself.

  • A woman with headphones sits thoughtfully at a laptop
    AI in customer service30 October 2026 · 5 min read

    Disclosing AI without breaking the conversation

    A disclosure has to be clear, but it does not have to read like a package insert. A few rules for text, voice and the switch to a person.

  • Library reading room with desk lamps
    AI in customer service1 November 2026 · 5 min read

    Grounded answers: why a knowledge base keeps AI honest

    Search first, then write, then show the source: that is how a plausible answer becomes one you can check.

See Univerx on your own example.

In a demo we show the platform along your channels and requests, from AI agents to video, workforce scheduling and analytics.

Request a demoGet in touch

Online, in German or English, with no preparation on your side.