Univerx AI
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.
Building blocks
Predictive Routing in detail.
The building blocks at a glance – all in the same workspace and under the same administration.
Choose the goal
You set the KPI, such as first contact resolution, customer satisfaction or handling time.
Learn from history
The model recognises which combination of request and person has worked well so far.
Rules stay
Mandatory paths such as language or permission apply first; the AI optimises within them.
Compare
Set results with and without predictive routing side by side before you expand.
#The right person, not just the next free one
Classic routing asks: who is free and has the right skill? Predictive routing also asks: who is most likely to achieve the best result for this request?
You define the result. For customer service it might be first contact resolution, for retention the save rate, for advice the satisfaction score. The model optimises for exactly that KPI.
#How it works
- A contact arrives. Request, channel and other approved characteristics are known.
- Check the rules. Call distribution narrows the group: language, permission, skill.
- Score. Within the group, the model estimates who is likely to do best for the KPI.
- Match. The contact goes to that person, as far as wait time and occupancy allow.
- Learn. The outcome feeds into future scoring.

#Rules first, AI second
Predictive routing does not replace rules. Someone with a request in French goes to someone who speaks French. Someone who needs account data goes to someone with permission. Only within that group does the AI optimise.
That keeps routing traceable. Mandatory paths are documented; the AI decision concerns only who within the permitted group gets the contact.
#Fair and co-determined
A model that scores employees by results touches co-determination rights. In Germany, technical systems capable of monitoring performance or behaviour are subject to works-council co-determination (Section 87(1) no. 6 BetrVG).
#Prove the impact
Before you expand predictive routing, compare. Some contacts run with it, some without. The reports show the chosen KPI for both groups. Only when the difference is robust is the rollout worth it.
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.
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
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.
- AI Act
- DSGVO
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
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
Which data does the model use?
Characteristics of the contact, such as request and channel, and the outcomes of past contacts. You decide which characteristics are used; special categories of personal data stay out.
Does routing permanently favour certain agents?
Routing still watches occupancy and wait times. Nobody receives every contact just because the model ranks them highly for a KPI.
How do we know whether it works?
With a comparison: some contacts with, some without predictive routing. The reports show the chosen KPI for both groups.
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.



















