Assistants

Each assistant has its own detailed interface, which is divided into several thematic subsections. These allow users to manage configuration, analyze performance, respond to feedback, or track change history in a clear manner.

Below you will find a description of the individual tabs of the assistant detail according to the current application layout (Overview, Configuration, Interface, Prompts, Analysis, Evolution, Conversations, Feedback, History).

Overview

The Overview tab represents a central panel that summarizes key information about the assistant on a single screen. Here, users will find basic metrics on how often the assistant is used, what data it has connected, how much feedback it has received, and its current evolutionary state.

This overview allows for a quick assessment of how the assistant is functioning, what feedback it is receiving, and who is using it most frequently, without the need to navigate to individual detailed tabs. It is an ideal starting point for an immediate assessment of the health and usage of each assistant.

• Cards: Name (model, connection, description), Development, Feedback, Conversations (last 30 days), and User Conversations (Top 5).
• Serves for a quick check of the assistant's status; "View More" links lead to details.
• Screenshot:
  

Configuration

The Configuration tab is used for the detailed setup of the assistant - that is, its technical configuration, default behavior, and integration with other platform features. This section allows for precise definition of how the assistant should behave, what data it works with, what model it uses, and what tools it has available.

Users set basic information about the assistant here, including its name, instruction description, system messages, and the model to be used (e.g., GPT-4o). Access to data is also defined here - either global access to all sources or limited access to selected datasets.

The configuration also includes a model layer, where parameters such as response creativity (temperature), repetition penalties, or maximum output length can be adjusted. These options allow for fine-tuning the assistant's behavior according to specific purposes or expectations.

In this section, it is also possible to connect the assistant to tools that it can actively use - for example, for connecting to a calendar, API, or other systems. The entire configuration is designed to allow the assistant to be quickly launched and also modified or versioned at any time.

• Name: the name of the assistant displayed in overviews, searches, and in the list of assistants.
• Description: a brief description of the assistant's purpose; helps with orientation within the team.
• Chatbot Tool: choice of provider/connection (Assistant Connection), which makes available models accessible.
• Model Name: specific model from the selected provider.
• Data connection: connection to data collections from the Data Collections section; determines what knowledge the assistant can work with.
• Access: visibility and team settings; Organization = everyone in the organization, Shared = selected users/teams, Private = only you.
• Preview: preview of the assistant's icon in the list.
• Change icon: selection of a custom icon.
• Recommended icons: quick presets of common icons.
• Icon color: color of the icon.
• Temperature: degree of creativity/variability; lower value = more consistent responses.
• Maximum Length: limit on the length of generated responses (shortens outputs and monitors costs).
• Presence Penalty: penalizes topic repetition; encourages new information.
• Frequency Penalty: penalizes repetition of words/phrases; reduces redundancy.
• Initial Message: introductory message displayed at the start of a new conversation.
• System Message: main system prompt defining the assistant's role, tone, and rules.
• Shared Tools: tools shared within the organization that the assistant can use.
• Private Tools: private tools available only to you.
• Subassistants: connection of additional assistants for delegating specific tasks.
• Enable public chat: makes the assistant accessible outside the main application.
• Enable Authenticated Chat Widget: allows embedding a chat widget on an external website with Google login.
• Save as Template: saves the current assistant as a reusable template for further creation.

The platform allows saving the currently created assistant as a template, which can then be reused when creating other assistants. This feature supports repeatability, consistency, and scalability of configurations across the organization.

After clicking the Save as Template button, a modal window will appear where the user fills in:

• Name – the name of the template.
• Description – a brief description of its focus and use.

The saved template will then appear in the overview when creating a new assistant and can be edited or reused at any time.

Interface

The Interface section allows setting how the assistant will be made available to end users. Here, it is defined how and where communication with the assistant should be possible, whether internally, via API, or publicly through integration channels and widgets.

• Public Chat switch with generated Chat URL (copy button).
• Web Plugin: embeddable script for embedding public chat on an external website.
• Settings: settings for feedback, file uploads, and a link to the privacy policy.
• Chat widget with authentication switch and Google Client ID field for embedding with login.

Prompts

The Prompts section is used to control the logic and behavior of the assistant through so-called system instructions. Here, the user defines how the assistant should respond, what stance it should take, communication style, or structure of responses.

Each prompt represents a specific instruction block that the model receives before processing the user's input. The assistant uses it to orient itself on what role to play, which information to prioritize, and what responses to generate.

• Table of all prompts; Create Prompt button for creating a new one.
• After creation, you can manage the prompt text and execution schedule.

Analysis

The Analysis section provides a detailed view of the technical and operational parameters of the assistant. Users will find summary statistics and visualizations here that help understand how the assistant is being used, its load, and its performance over time.

Monitored metrics include the number of requests, volume of consumed tokens, ratio of input to output tokens, response processing speed, and other indicators. This information is available in the form of clear graphs and bar visualizations, which allow for identifying trends, fluctuations, or potential anomalies.

Analyses are a crucial tool for administrators and product teams who want to not only operate assistants but also optimize them. They help evaluate when the highest usage occurs, what the consumption-to-performance ratio is, and how quickly the assistant responds under real conditions.

• Section for an overview of the assistant's performance (volume and quality of interactions).

Evolution

The Evolution section allows managing the development of the assistant's system instructions (prompts) based on real behavior and feedback. Administrators can compare individual versions of prompts here, evaluate their impact, and apply changes in a targeted and controlled manner.

The main part consists of comparing the currently active prompt with a proposed modification. The user can thus see the previous and new wording of the instruction side by side and easily identify how the assistant's logic is changing. In addition to textual comparison, the system collects specific use cases on which the change can be tested.

The evolution section also includes an overview of feedback that led to the change or to which the new version of the prompt should respond. This feedback includes ratings, comments, and the identity of the users who submitted it.

Evolution is thus a tool for improving the assistant's behavior based on data, not intuition. It allows for continuous development, controlled testing, and documentation of all changes over time.

• Overview of user suggestions for prompt evolution (date, user, message, rating).
• Develop action (suggests modifications) and Apply Evolution action (applies changes).

Conversations

The Conversations section serves as an overview of all interactions that have taken place between users and a specific assistant. Users will find a list of conversations with information about the date, initiating user, topic, and total number of messages within that exchange.

This section provides administrators with the opportunity to delve into the specific content of communication, analyze how the assistant is used in practice, and verify how queries were answered. The displayed information can be used for further evolution of the assistant, fine-tuning prompts, or ensuring compliance with internal rules.

Each conversation includes the option for a detailed view. Users can thus retrospectively track the entire communication, including all steps and responses, which increases transparency and allows for backtracking when needed.

• List of conversations with users: date, user, subject, number of messages; the eye icon opens the thread detail.

Feedback

The Feedback section serves as a centralized overview of the feedback provided by users on the assistant's responses. Each record includes the date, user identity, interaction outcome, and type of rating - for example, positive, negative, supplemented by a comment, or other specific ratings.

Thanks to this section, administrators can easily identify responses that were inaccurate, misleading, or particularly beneficial. All reactions are traceable, and it is possible to look back at the context in which the rating occurred.

This feature is crucial for the future evolution of the assistant - it provides a data-driven basis for prompt adjustments, refinement of data context, or evaluation of training needs. In combination with the Evolution section, it forms part of the continuous improvement of the assistant's outputs.

• Collected ratings and comments on the assistant's responses.

History

The History section serves to transparently track all important changes that have been made to the assistant. Each record includes the date, author of the change, affected entity, and type of action performed.

This audit trail is important for operational oversight, security standards, and backtracking interventions in an environment where assistants often undergo evolution or modifications.

• Audit log of actions on the assistant (date, user, entity, type of action).
• Allows tracing modifications of models/prompts/data connections.
• Screenshot: