Information for users
chatsPromptsProgram settings
Information for administrators
admin areaSSO with SAML 2.0
useful information
In generalAI models

Chat settings

Standard AI model

The standard AI model is the model that is used by default when starting a new chat (1). From a drop-down menu, you can select from various AI models (1a) choose. Choose the model that best suits your needs.

In addition, it is still possible to adjust the AI model for each individual chat in the associated chat settings. You can read how to do that here.

Choose the right AI model

To work effectively, you only need two different AI models - a strong model such as OpenAI gPT4-o or Claude 3 Opus, and a weak model such as GPT 3.5 Tubo or Claude 3 Haiku.

You always use the strong model when your prompts involve complex relationships, for example when there are many dependencies or conditions. On the other hand, if you work with clear, simple instructions, you can choose a weak model. The advantage of these weak models is that they require significantly fewer credits for the same amount of words.

Default pseudonymization

Pseudonymization (2) Can via the control element (2a) be switched on and off.

In addition, it is still possible to adjust the pseudonymization for each individual chat in the associated chat settings.

What is pseudonymization?

Pseudonymization processes personal data in such a way that it can no longer be directly assigned to a specific person without additional information. The pseudonymization feature of provides additional protection for personal data that you use when making inquiries to the AI model.

This data is pseudonymized

Where technically recognizable, this function replaces personal information such as e-mail addresses, IBANs, credit card information, ID numbers, vehicle license plates and IP addresses as well as full names before transmission and reinserts them after receiving the message. Pseudonymization is carried out through pattern recognition using regular expressions, name databases and natural language processing.

Activate and deactivate pseudonymization

Pseudonymization can be activated and deactivated at any time. It may be necessary to turn off the feature if you are looking for information about a public figure and need real data, such as their name, in order to conduct proper research.

Even when the filter is switched off, complies with data protection regulations

Pseudonymization serves to increase the level of data protection and has no influence on the security of your data. Regardless of the status of the function, your information is stored exclusively on the servers and is never used to train the AI models.

Embossing default

The embossing (3) allows you to customize the AI personality of and tailor it to your needs. The AI takes on a role assigned by you, from which it then acts.

With such embossing, you can automate repetitive tasks, for example. This would include: “You translate every text you enter into English according to (...) the following rules. Your answers consist only of the translation, without any additional information.” Another example of embossing is: “You are a psychologist and check the mood of the entered text. You only answer “positive,” “neutral,” or “negative.” You don't give a reason and only answer with that one word.”

Here you can do a standard embossing (3a) Set which is used for all of your requests to the AI. To do this, enter the text that you want to give the AI as an instruction and then confirm with “Save embossing” (3b).

In addition, it is still possible to adjust the embossing for each individual chat in the associated chat settings. Please also read the Chat settings article.