Chat settings

Opening chat settingsOpen chat settings

You can adjust various settings during your chat with nele.ai. Click on the gear icon in the bottom left of the chat window (1) to open the chat settings.While chatting with nele.ai, you can adjust various settings. Click on the gear icon at the bottom left of the chat window to open chat settings.

‍

Here you will find the options for web search (2), pseudonymization (3), persona (4), AI model selection (5), reasoning settings, and knowledge bases (6), provided that knowledge bases are enabled for you.Here are the options for web search , pseudonymization , embossing , the AI model selection , the reasoning setting and the knowledge databases , provided that knowledge databases are activated for you.

Web searchWebsearch

The web search feature allows nele.ai to retrieve current information from the internet and incorporate it into its responses. This feature must be enabled by your administrator before it can be used.The web search function enables nele.ai to retrieve current information from the internet and incorporate it into responses. This feature must be authorized by your administrator before it can be used.

‍

How web search worksHow web search works

‍

When you have enabled web search and enter a prompt, search terms are automatically generated and sent once to an AI-based search engine. The search results are then summarized into a comprehensive answer by the currently active AI model. The answer includes sources as well as up to 5 links to external websites.When you have activated web search and enter a prompt, search terms are automatically generated from it and sent once to an AI-powered search engine. The search results are then compiled by the currently active AI model into a comprehensive response. Both sources and up to 5 links to external websites are displayed in the answer.

‍

Country setting for web searchCountry setting for web search

‍

When using web search for the first time, you can select the country from which the search query should be sent to specify the results. This setting influences the relevance and regional focus of the search results. The selected country can be adjusted at any time later in the chat settings.When using web search for the first time, you can select the country from which the search query should be sent to specify the results. This setting influences the relevance and regional focus of the search results. The selected country can be adjusted at any time later in the chat settings.

‍

Activating web searchActivating web search

‍

Web search can be switched on and off via a control element. If the feature is not visible in your chat settings, it has not yet been enabled for you by your administrator.Web search can be turned on and off via a control element. If the function is not visible in your chat settings, it has not yet been authorized for you by your administrator.

Pseudonymization of personal dataPseudonymization of personal data

Pseudonymization can be switched on and off via a control element.Pseudonymization can be turned on and off via a control element.

What is pseudonymization?What is pseudonymization?

During pseudonymization, personal data is processed in such a way that it can no longer be directly attributed to a specific person without additional information. The nele.ai pseudonymization feature provides additional protection for personal data that you use in queries to the AI model.In pseudonymization, personal data is processed in such a way that it can no longer be directly attributed to a specific person without additional information. The pseudonymization feature of nele.ai provides additional protection for personal data that you use when making requests to the AI model.

This data is pseudonymizedThis data is pseudonymized

Where technically detectable, this feature replaces personal information such as email addresses, IBANs, credit card information, ID numbers, vehicle license plates, and IP addresses, as well as full names, before transmission and re-inserts them after the message is received. Pseudonymization is performed through pattern recognition using regular expressions, name databases, and natural language processing.This feature replaces, where technically detectable, personal information such as email addresses, IBANs, credit card information, ID numbers, license plates, and IP addresses as well as full names before transmission and reinserts them after receiving the message. Pseudonymization is performed through pattern recognition using regular expressions, name databases, and natural language processing.

Activating and deactivating pseudonymizationEnabling and disabling pseudonymization

Pseudonymization can be activated and deactivated at any time. It may be necessary to switch off the feature if you are searching for information about a public figure and require real data, such as their name, to conduct an accurate search. The feature can also be used in conjunction with web search, though in this case, it may affect the quality of the query.Pseudonymization can be enabled and disabled at any time. It may be necessary to turn off the function when you are searching for information about a public figure and need real data, such as their name, to conduct proper research. The feature can also be used in conjunction with web search, but may affect the quality of the query in this case.

nele.ai is data protection compliant even when the filter is switched offnele.ai remains privacy-compliant even with the filter disabled

Pseudonymization serves to increase the level of data protection and has no impact on the security of your data. Regardless of the feature's status, your information is stored exclusively on nele.ai servers and is never used to train the AI models. Pseudonymization serves to increase the level of data protection and has no impact on the security of your data. Regardless of the function's status, your information is stored exclusively on nele.ai servers and is never used for training AI models.

Functional descriptionFeature description

The pseudonymization feature is optional and provides an extra layer of data security. Please note that the results do not depend on the use of this pseudonymization feature. Data protection compliance is maintained even if the pseudonymization feature is not used. The functionality of the pseudonymization feature is described and explained below: The pseudonymization feature is optional and provides additional data security. It should be noted that the results do not depend on using this pseudonymization feature. Privacy compliance is maintained even when the pseudonymization feature is not used. The following explains and describes how the pseudonymization feature works:

‍

If required, unique personal information in user queries can be replaced by anonymous placeholders before transmission. This applies to first and last names, phone numbers, email addresses, IBANs, credit card details, ID numbers, license plates, and IP addresses. Administrators can enable pseudonymization globally in the admin backend as the default setting for all new chat sessions within their team. Users also have the option to set pseudonymization as the default for their new chat sessions in their application settings. The feature can also be toggled on or off directly in new and active chats, with this individual setting overriding the global one.

The pseudonymization process involves a local pre-check of chat queries in text form (graphical text representation is not included) for sensitive content before they are forwarded to the AI models. Sensitive data is identified using a regular expression (RegEx) method, where user queries are compared against various predefined patterns and a database currently containing 11,000 first and last names. Matching content is replaced by numbered placeholders such as [[lastname_placeholder_001]]. This method allows the AI models to interpret the texts correctly without needing access to specific personal information. The numbering of the placeholders ensures precise re-translation later. The breakdown of the placeholders used and the original content: The pseudonymized messages are then sent to the AI models for processing. Upon receiving the responses, they are checked for the assigned placeholders and replaced locally with the original information. During the streaming of AI responses, users see the text including placeholders, allowing them to follow the process. It is possible that personal data may not be recognized. This can happen if all characters of an input do not exactly match one of the stored patterns or if a name is not contained in the database. Such cases can be triggered, for example, by unexpected spellings with spaces or special characters. Anomalies in pseudonymization can be reported via a contact form. This allows for the adjustment of patterns and name databases.When needed, unique personal information in user queries can be replaced with anonymous placeholders before transmission. This affects first and last names, phone numbers, email addresses, IBAN numbers, credit card data, ID numbers, vehicle registration numbers, IP addresses. Administrators can globally enable pseudonymization in the admin backend as the default setting for all new chat conversations of their team. Users also have the option to set pseudonymization as the default for their new chat conversations in the application settings. The feature can also be turned on or off directly in new and active chats, with this individual setting overriding the global ones.The pseudonymization process includes a local preliminary check of chat requests in text form (graphical text representation is not included) for sensitive content before they are forwarded to the AI models. The identification of sensitive data is performed through a regular expressions procedure (RegEx procedure), where user requests are compared with various predefined patterns as well as a database of currently 11,000 first and last names. Matching content is replaced with numbered placeholders like [[lastname_placeholder_001]]. This method allows AI models to correctly interpret the texts without having to access specific personal information. The numbering of placeholders ensures precise later retranslation. The breakdown of used placeholders and original content The pseudonymized messages are then sent to the AI models for processing. After receiving responses, they are checked for assigned placeholders and locally replaced with the original information. During streaming of AI responses, users see the texts including placeholders and can thus follow the process. It may happen that personal data is not recognized. This can occur when all characters of an input do not exactly match one of the stored patterns or when a name is not contained in the database. Such cases can be triggered, for example, by unexpected spellings with spaces or special characters. Anomalies in pseudonymization can be reported via a contact form. This enables adjustment of patterns and name databases. To strengthen transparency and trust in the pseudonymization process, users can see the texts including placeholders during streaming of AI responses. This allows them to verify the correct application of pseudonymization.

Verification of pseudonymization reliabilityTesting the reliability of pseudonymization

Based on tests conducted by the controller, the pseudonymization function achieves an effectiveness rate of 98.43%. This means that in 98.43% of cases, pseudonymization was performed correctly by reliably replacing all sensitive data with placeholders, meeting data protection requirements. Taking all tested cases into account, including those where over-pseudonymization occurred, the overall success rate is 95.29%. This broader assessment includes cases where the pseudonymization function still showed certain irregularities in the exchange or assignment of placeholders.Based on tests conducted by the data controller, the pseudonymization feature achieves an effectiveness rate of 98.43%. This means that in 98.43% of cases, pseudonymization was performed correctly by reliably replacing all sensitive data with placeholders, meeting data protection requirements. Taking into account all tested cases, including those where too much was pseudonymized, the overall success rate is 95.29%. This additional consideration includes cases where the pseudonymization feature still showed certain irregularities in the exchange or assignment of placeholders.

PersonaEmbossing

A persona allows you to customize the AI personality of nele.ai and tailor it to your needs. The AI adopts a role assigned by you, from which it then operates.An imprint allows you to customize the AI personality of nele.ai and tailor it to your needs. The AI takes on a role assigned by you, from which it then acts.

Using such a persona, you can, for example, automate repetitive tasks. This could include: "You will translate every entered text into English according to the following rules (...). Your responses consist only of the translation, without additional information." Another example of a persona is: "You are a psychologist and you check the entered text for its mood. You respond exclusively with 'positive', 'neutral', or 'negative'. You provide no justification and respond only with this one word."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.”

In the text field (1), you can customize a persona by entering your own instructions for the AI's personality. Once you make an adjustment, it is applied automatically. You also have the option to save this persona as your default (2). Once saved as the default, it will be applied to the current chat and all new chats with nele.ai. You can change the persona at any time in the chat settings. You can also view the default persona in the program settingsProgram settings.In the text box You can customize an imprint by entering your own instructions for the AI personality If you make an adjustment, it is automatically adopted. You can also save this embossing as a standard embossing . If you have saved the default embossing, it will be applied to current and all new chats using nele.ai. You can change the embossing at any time in the settings of a chat. You can also use the standard embossing in the view.

AI modelAI model

You can choose from various language models that define the AI's behavior and capabilities. Select the appropriate model for your use case, e.g., for programming, creative writing, etc. You can choose from various language models that define the behavior and capabilities of AI. Choose the right model depending on the application, e.g. for programming, creative writing, etc.

Choose the right AI modelChoose the right AI model

For effective work, you basically only need two different AI models: a powerful model such as OpenAI GPT-4o or Claude 3 Opus, and a lighter model such as GPT-3.5 Turbo or Claude 3 Haiku. 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.

Always use the powerful model when your prompts involve complex relationships, such as those containing many dependencies or conditions. Conversely, if you are working with clear, simple instructions, you can choose a lighter model. The advantage of these lighter models is that they require significantly fewer credits for the same amount of text.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.

Reasoning

For selected AI models, you have the option to adjust the intensity of the reasoning process. Reasoning refers to the AI model's ability to think through complex problems step-by-step before generating a final answer.With selected AI models, you have the option to adjust the intensity of the reasoning process. Reasoning is the ability of the AI model to think through complex problems step by step before generating a final answer.

What is reasoning?What is reasoning?

During reasoning, the AI model analyzes your request in several steps and weighs different approaches before reaching a conclusion. This leads to more precise and well-thought-out results, especially for complex logical, mathematical, or analytical tasks.In reasoning, the AI model analyses your request in several thought steps and weighs up various solutions before reaching a conclusion. This leads to more precise and well-thought-out results, particularly when it comes to complex logical, mathematical or analytical tasks.

Adjust reasoning levelsSet reasoning levels

For models with configurable reasoning, you can choose between different intensity levels. The available options are displayed as a dropdown menu in the chat settings:For models with configurable reasoning, you can choose between different intensity levels. The available options are shown as a drop-down menu in the chat settings:

‍

• Standard configurationStandard configurationThe model operates with minimal or no reasoning effort. This setting corresponds to standard response behavior and is preselected by default when starting a new chat with a reasoning model. It is suitable for simple queries and maintains the familiar response speed.
• LowLow: A reduced reasoning effort for tasks with lower complexity.
• MediumMedium: A balanced reasoning effort for moderately complex questions.
• High: An intensive reasoning process for particularly demanding, multi-layered, or logically complex problems.

For some models, the reasoning intensity is fixed by the provider and cannot be adjusted manually. In these cases, only the standard configuration is displayed.For some models, the reasoning intensity is fixed by the provider and cannot be adjusted manually. In these cases, only the default configuration is shown.

When should reasoning be used?When should reasoning be used?

Reasoning is particularly helpful for:Reasoning is particularly helpful for:

‍

•              Complex logical reasoning
•              Mathematical calculations and analyses
•              Multi-step problem solving
•              Tasks that require a structured approach

For simple requests such as short text summaries, translations, or information retrieval, the standard configuration is usually sufficient.For simple inquiries such as short text summaries, translations or information requests, the standard configuration is usually sufficient.

Knowledge basesKnowledge databases

Under the "Knowledge base" section, you can select which data sources the AI assistant should use for its responses. This allows you to control the information base the AI uses to generate its answers.Under “Knowledge Base”, you can select which data sources the AI Assistant should use for its answers. This allows you to control the information base on which AI builds its answers.

For example, you can use company-specific documents or websites that have been provided by your administration. This allows you to receive more precise and relevant results for your queries.

If you do not see the knowledge base field, this feature is not included in your plan.For example, you can use company-specific documents or websites that were previously provided by your company by an administrator. In this way, you get more accurate and relevant results for your inquiries.If you don't see the Knowledge Base field, this feature isn't included in your functionality.

For more information, please see our articles on knowledge basesknowledge databases and the difference between knowledge bases and chat contextDifference between knowledge bases and chat context. Administrators create knowledge bases in the admin areaadmin area.Please also read our articles on the subject and the . Administrators create knowledge bases in