Skip to main content
The AI Control Center is the central place to provide transparency for the performance and control of Enneo’s AI agents. It shows how reliable the AI agents are operating, what the level of automation is, and where there’s additional potential.Automations accelerate the processing of customer concerns, reduce process costs, and relieve customer service employees, who can focus on complex cases.The Control Center makes it clear which business transactions are already being handled by AI, where human approvals are sensible, and what steps are possible in terms of fully autonomous processing.It makes this development measurable, understandable, and manageable, providing the key to gradually expand automation in customer service.

​
Requirements for Viewing and Using

  • General access: Authorization in the area Data and Reports → AI Control Center
  • Automation settings: Access for configuration, ticket detection, and triggering is controlled via permissions in the Dark processing area
  • Quality check: Authorization in the AI Quality Check area, controls access to views, execution of test runs, and their processing
  • Live overview: Authorization in the area Tickets → Ticket Overview Page
  • AI Agent Team: Authorization in the AI Agent Management area controls access to views, creation, and editing possibilities

​
Tools in Overview

The AI Control Center brings together the most important tools for automation in one place:
  • Live Overview & Metrics: Overview of live key figures, degree of automation, and AI agent performance → learn more
  • Quality check: Management of test cases and evaluation of test runs → learn more
  • Automation settings: Control of automation levels with and without release → learn more

​
Stages of Automation

The goal is the fully autonomous processing of business transactions by AI agents.
The journey there involves several stages:
  1. Manual processing
    The AI agent fully recognizes the request, correctly reads out the relevant data, derives suitable processing options and makes them available. A human decides on the further action(s).
  2. Dark processing with release
    The AI agent takes over all steps of processing: It recognizes the concern, reads out the data, derives the correct action, and selects the appropriate processing option. The examiner only needs to approve the selection made by the AI agent with one click, or reset the process to manual processing if deviations are noticeable.
  3. Dark processing without release
    The AI agent takes over processing completely autonomously: It recognizes the concern, reads the data, derives the appropriate action, selects the correct processing option, and executes it independently.
The stages of automation build on each other.The transition to the next level only makes sense when the first level works reliably.Especially in the first two stages, it’s therefore crucial to not just simply close cases, but to consciously analyze and rate them.This way, it can be determined whether and at which points the AI agent should be adjusted further, or whether the next automation level can be unlocked.

​
Example: Bank Data Agent

A rule-based AI agent was created for the purpose of processing customer concerns about bank account changes. It’s supposed to check whether the IBAN provided by the customer is already stored in the system, whether it’s invalid or whether it can be adopted as a new, valid bank connection. Initially, a processor manually decides on the performance of the AI agent:
  • Is the customer’s request correctly recognized (change of bank details)?
  • Are all relevant parameters correctly read out (IBAN, validity date, account holder)?
  • Are the typical use cases correctly covered? (IBAN valid, IBAN invalid, IBAN already present, validity date in the past)
  • Are the correct processing options offered? (Adopt IBAN, inform customer about errors in the IBAN, adjust validity date)
If the processor finds that individual points on the checklist are not reliably met, this is an indication that the bank data agent needs to be adjusted. This includes, for example, adjustments to the detection of input parameters, the optimization of the business logic, or additions to the output handling. Only when this feedback is implemented and the results are stable can the next automation step take place. If the bank data agent consistently shows correct results, it can be switched to Dark processing with release. If reliable results are confirmed here too, the switch to Dark processing without release, or fully autonomous processing, follows.

​
Preconditions and Risks

Before an AI agent is transferred to higher levels of automation, certain conditions must be met:
  • Reliable customer recognition
  • Accurate request recognition
  • Low error rates when recognizing and reading out parameters
  • Successful test runs in the quality check
Risks arise primarily when incorrect decisions go unnoticed in dark processing. The dashboard and the quality check help minimize these risks and detect errors in a timely manner.

​
Role of the Users in the Control Center

Users of the AI Control Center have different tasks:
  • Create test cases and maintain them to check the reliability of the AI agents
  • Monitor results and document and/or communicate any irregularities
  • Make assessments on whether an AI agent can be transferred to the next stage of automation