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.
Building blocks
AI Agents in detail.
The building blocks at a glance – all in the same workspace and under the same administration.
Understand
Recognise the request from free speech, ask back when something is missing, and stay on topic.
Act
Read and write in connected business systems: check a status, move an appointment, open a case.
Hand over
Where a person is needed, they hand over with a summary, the history and the open point.
Disclose
Identify themselves as AI in the dialogue and offer the way to a person at any time.
Log
Every action is recorded with time, source and result, analysable and deletable.
Govern
Built, tested and approved in Agent Studio, with versions and roles.
#What an AI agent is at Univerx
An AI agent is software that understands a request, acts in connected systems and hands over with context. That sets it apart from a chatbot that pulls answers from a list and gives up at the first deviation.
On the phone the same agent works as a voicebot, in chat as a text agent. One logic, many channels.
- Understand. "My decision letter does not match my application" becomes a request with a case and an open point.
- Act. The agent checks the case in the business system and prepares the correction.
- Hand over. If a decision is needed, the case goes to a person with a summary.
#Limits that are built in
An agent may only do what is approved in Agent Studio. Every action is logged. Disclosure as AI is not a switch that gets flipped by accident but part of the dialogue.
These limits are designed for the transparency duties of the EU AI Act. They do not replace a legal assessment of your deployment; the basics are under EU AI Act.
#Where teams use agents first
- Status enquiries, appointment changes, address changes: requests with a clear flow and a clear answer.
- Pre-qualification before handover: find the case, name the request, then route to the right person.
- Peak load: when everyone calls at once, agents answer the most common question immediately.
What agents should not take over is your call. A pilot with one request and one channel quickly shows where the line makes sense.
#What an agent needs
An AI agent is as good as what it may access. Three things decide its quality: the knowledge it answers from, the actions it may perform, and the rules for when it hands over.
| Building block | Where it comes from | Who maintains it |
|---|---|---|
| Knowledge | Univerx Knowledge and approved sources | Content editors |
| Actions | Interfaces to business systems | IT, approved by the business unit |
| Handover rules | Flow in Agent Studio | Service owners |
#Measuring whether it works
An agent succeeds when requests are resolved, not when as many conversations as possible end without people. Watch the resolution rate per request, drop-offs and what happens after handover. Conversation analytics shows where agents get stuck.
Univerx AI
AI that resolves requests and backs up people.
AI agents resolve routine requests on the phone and in chat, Univerx Assist supports employees live, Agent Studio governs it all. Plus routing, conversation analytics and knowledge; governance is part of the product.
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.
- AI Act
- DSGVO
Univerx Assist
AI assistance in the conversation: suggested replies, relevant knowledge, next steps and automatic summaries for agents. For team leads, an overview of topics and coaching needs.
- AI Act
- DSGVO
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.
- AI Act
- DSGVO
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.
- AI Act
- DSGVO
Predictive Routing
Every contact goes to the person most likely to achieve the best result for the chosen KPI. The model learns from past contacts; you choose the goal and keep the rules.
- AI Act
- DSGVO
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.
- AI Act
- DSGVO
- EU
Agentic AI
AI agents that complete multi-step tasks across connected systems: look up, change, book, trigger a process. Several specialised agents, coordinated by an orchestrator, bound by guardrails and approvals.
- AI Act
- DSGVO
Natural AI voices with ElevenLabs
Studio-quality voices in many languages and accents, fast enough for live dialogue. For voicebots, announcements, notifications and read-aloud. With ElevenLabs as technology partner, always disclosed as AI.
- AI Act
- DSGVO
- BFSG
Real-time translation
Chat, messaging, email and calls in the customer's language, while agents work in their own. Translated both ways in real time, with a glossary for specialist terms and a transcript in both languages.
- DSGVO
- AI Act
Supervisor copilot
AI summarises what is happening in the queues: topics, emerging issues, sentiment trends, compliance risks. It suggests actions, writes the shift summary and answers questions in natural language. Without individual surveillance.
- AI Act
- DSGVO
Authentication & fraud protection
Verify identity at the start of the contact: by app confirmation, one-time code, knowledge question or, with consent, voice traits. The status holds for IVR, bot and agent, and anomalies are flagged.
- DSGVO
- eIDAS
- AI Act
Frequently asked questions
How does a customer know they are talking to AI?
The agent says so at the start and repeats it when asked. Switching to a person is possible at any time and is never hidden.
What happens when the agent gets stuck?
It hands over with context: summary, history so far, open point. Nobody has to tell their story a second time.
Can the agent really do something in our systems?
Yes, through connected interfaces and only within the approved actions. You define those in Agent Studio.
Related
Use casesSelf-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.
Use casesCustomer service
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.
IndustriesPublic 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.
IndustriesUtilities & 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.
Guides2 November 2026 · 11 min readIntroducing 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.
GlossaryAI agent
An AI agent is software that understands a request in natural language, acts in connected systems and hands over to a person when a decision or empathy is needed.
GlossaryAgentic AI
Agentic AI receives a goal instead of a single instruction. It breaks the goal into steps, uses approved tools and checks interim results. Its value grows, and so does the need for limits and oversight.
GlossaryIntent recognition
Intent recognition determines which request lies behind an utterance, whether spoken, typed or emailed. It is the basis for bots that answer and contacts that reach the right place.
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.
Online, in German or English, with no preparation on your side.