The Basic-Agent is a key element of AI-based automation in Enneo. It analyzes incoming customer concerns, accurately recognizes their mood, subject, and context. Thus, serving as a foundation for all subsequent decisions - from intelligent routing to delegation of standard processes to the appropriate AI agent.If the concern cannot be handled by another AI agent, The Basic-Agent generates a suitable response proposal. It uses similar concerns from the past and stored articles in the wiki for reference. It learns with each use and continuously improves itself in this way.Via the Prompt, the tone, address, and response behaviour can be controlled, as well as defining how the basic agent formulates, which content it responds to, and how it acts in case of uncertainty. For each communication and sub-channel, a separate basic agent with specific behaviour can be stored.

​
Basic Configuration

The basic configuration of the Basic-Agent follows the same principle as for AI agents with Smarter Argumentation logic. The central component is the Prompt: It determines how the Basic-Agent proceeds and which tools it can access.
If no language instructions are given in the prompt, the basic agent is based on the default language in the section Advanced Settings → General → Language

​
Individual Prompt Settings

The prompt of the Basic-Agent describes the basic behaviour: how a concern is processed, which tools are used, and which structure is used. It is the shared, reusable logic for all use cases. In addition, supplementary instructions can be stored in the section AI Customization → Miscellaneous → Individual Prompts. These are taken into account in addition to the Basic-Agent’s prompt when generating responses. They enable a demand-driven representation of special rules and specifications, linguistic details, or client-specific peculiarities without having to customize the basic agent itself.

​
Assignment to Communication Channels

The Basic-Agent can be directly linked to a communication channel, for example, to a specific email mailbox, a chat, or a telephone channel. The assignment is made in the settings of the respective sub-channels in the section Communication Channels and allows a tailor-made, client-specific configuration. In this way, different variations of the Basic-Agent can be run in parallel, each with its own tonality in the response suggestions, own toolset, and wiki access. Example: The Voltlingen Basic-Agent is linked to the email account service[at]sw-voltlingen.de. It formulates the response suggestions casually in the form of “you”, accesses FAQ articles specifically for the Stadtwerke Voltlingen, and is familiar with the product peculiarities there. Meanwhile, the Stromhain Basic-Agent working under service[at]sw-stromhain.de uses formal addresses, a different selection of knowledge base categories, and has its own rules for handling certain topics. Both basic agents are based on the same technical foundation but are fully tailored to each client.
This option opens up a high level of flexibility: Several brands, locations, or target groups can be individually cared for with only one instance, without compromises in style, sources of knowledge, or approach.