Zive Assistants are customized helpers you can set up to make your life easier and become more productive and efficient. You can see assistants as your work companions for a all kinds of use cases, helping you with tasks, support your decision making, analyzing data and much more.
The biggest benefit of assistants is that once configured, often very simple and short prompts by users deliver exceptionally valuable results. So assistants really provide the biggest value for repetitive tasks that teams face or topics that users always ask questions about which then need to be answered by experts. Zive Assistants can be instructed on exactly these tasks and topics providing efficient solutions for employees.
Tip: This article is focused on the functionality of Zive Assistants. If you are looking for ideas and examples for assistants, take a look at our dedicated article Inspiration for Zive Assistants.
How to create an assistant
Assistants have their own section which you find in your navigation bar. Here you find an overview of the available assistants with your favorites starred at the top. To create an assistant you find the button "Create new" in the top right corner.
After clicking the button you can choose in which space you want to create the assistant. This defines who can access your assistant after you published it.
Your space (Personal):
Every user has the permission to create an assistant in their personal space
Assistants created in your personal space are only available to you
Company space:
Only users with the platform role "Moderator" can create assistants in the company space
Assistants created in the company space are available to all users
Team spaces (if existent):
Only users assigned as "Managers" of the respective team space can create assistants in the space
Assistants created in a team space are available to all members of the respective space
You can also navigate into a space and create an assistant there. To learn more about Spaces and their configuration, read our dedicated help article.
In the slider that opens you can give basic information about your new assistant. You need to provide a name and a description and can select an icon and the color for your agent. You also have the possibility to define Managers that should be able to edit the agent. All of the information can be adjusted afterwards as well. Click on "Continue" to start defining the detailed settings for your new assistant.
How to configure an assistant
Tip: Use the preview on the right side to test how your adjustments to the configurations impact the behavior and results of your assistant.
Settings
In the first tab you can adjust the basic information you just defined, like name and description. Those settings are quite self-explanatory, but there are three more configuration options that are quite important and valuable.
Welcome message
The welcome message is the first thing users will when entering the assistant. Therefore it's important to define a message that helps users to immediately understand what the assistant can do and motivate them to try it out.
Tip: You can use the variable "<user/>" to integrate the name of the respective user in the welcome message and address users personally.
Conversation starters
Conversation starters are extremely valuable from a user perspective, especially if you create an assistant for your team (in a team space) or the entire company (in the company space).
With conversation starters you provide users prompt templates. Instead of writing a prompt themselves they can simply click a button, making it much easier for them to start a chat. Additionally this way you can ensure that the input prompt of the user is aligned with the assistant's instructions in the background.
Tip: When configuring an assistant take the perspective of a user who sees it for the first time and does not have access to the settings.
Is it clear what the assistant can do?
Would I know how to start a conversation?
Is it easy to understand specific requirements (e.g. additional input to be provided)?
Access settings
The access settings at the end of the tab allow you to define precisely who should be able to see and access the assistant and when.
Hidden: This toggle gives you the possibility to hide your assistant while you are setting it up or testing it. While this is toggled on, the assistant is only visible to the creator and managers (if set).
Managers: Through adding users as managers for an assistant you allow them to edit the settings. This is great if you want to collaborate with others on creating an assistant, without assigning them a permanent role (e.g. Global Moderator or Space Manager for team spaces). Deleting an agent is only possible for the creator, not managers.
Space: You can always adjust in which space an agent belongs. This allows you to quickly adjust the visibility and accessibility to a new user group.
Knowledge
In the "Knowledge" tab you can add relevant context to the assistant. For most use cases there is some kind of information or guidance that is relevant and needs to be considered by your assistant. This is the place to define it.
Think about which information and context is always required by the assistant to perform its task. For example this could be knowledge the assistant should use to answer user questions or templates that provide orientation for the assistant how to approach the task or in which format to generate the output.
The token usage always indicates how much of the context window is consumed by the knowledge you attached.
As long as you are below the limit all of the attached context is always loaded into the content for the AI model.
As soon as the limit is exceeded the assistant automatically gets equipped with the "search company knowledge" capability, and will restrict this search to only the attached knowledge.
There are different sources from which you can add knowledge to your assistant:
From company knowledge
To add content that is already available on the platform, e.g. through the connected integrations. There are two different options to access the company knowledge and find what you want to add:
Search: If you know exactly which relevant content items the assistant should consider, you can enter a search term to quickly find and select them.
Browse: Ideal if you know there is relevant context but don't know the exact name or it's not only single content items. It allows you to browse through your integrated systems and select the content on every hierarchy level (e.g. entire folders).
Tip: If there is a lot of relevant knowledge and not all of it in one folder, it's often useful to first create a Zive Collection in which you collect all relevant information about a topic, and then attach the collection to the assistant. This brings a couple of benefits:
Easier to organize content in collections
Content can also be explored by users in the collection
Collection can be used in multiple assistants/agents potentially
Upload local files
If relevant files that are not indexed into the platform, but available on your device, you can quickly upload them directly into the assistant context.
Keep in mind that compared to content that you attach from the company knowledge, local files uploaded are static and not updated automatically. You should see this as a secondary option compared to the company knowledge.
Note: Local files uploaded into an assistant become accessible for all users with access to this assistant. Deleting an assistant removes local files uploaded from the platform again.
Capabilities
Think of the assistant as a customized companion. You already provided the required information in the "Knowledge" tab, now you equip it with the capabilities it needs.
Core capabilities
There are four default capabilities that you can activate for your assistant:
Search company knowledge: This lets you define whether or not the assistant should perform an internal search. Activate this if you expect the assistant to do research across the entire internal knowledge. On the other hand, if you expect the assistant to use very specific sources as context add them in the Knowledge tab instead and deactivate this capability to avoid the risk of the assistant using other information.
Auto Pilot: Here you can define whether the assistant should first return the sources qualified as relevant during the internal research and have the user confirm them (auto pilot off) or directly generate the answer without user confirmation of the relevant sources (auto pilot on).
Search web: Allows the assistant to search relevant information from the web. Should be activated if the assistant needs external, up-to-date information in order to perform its task.
Data analyst: This enables the assistant to execute code, e.g. in order to create graphs or analyze data. Whenever you expect your assistant to perform complex tasks or solve complex problems this capability will be required to achieve ideal results.
Image generation: If activated on platform level, assigning this capability enables the assistant to create images as (part of the) output.
Tip: More is not always better! Less tools mean less options for the AI model to choose the correct one from.
Integrations
Note: Which integrations and respective actions are available depends on the configuration by your Admins.
In addition to the general capabilities you can activate specific integrations for your assistant. This makes sense if you want the assistant to interact with specific systems to retrieve additional information or create/update information.
Click on "Add integration" to see a list of the available systems and actions to choose from.
Select the actions the assistant needs in order to fulfill its purpose. After you selected actions you can click on the pen icon on the right side to configure whether this action should run automatically. Don't forget to save adjustments you make.
Tip: See capabilities and especially integrations as tools you equip your agent with. Your instructions need to guide the assistant when and how to use these tools.
Behavior
Last in order, but definitely not least. In the previous tabs you defined the framework conditions for your assistant: the appearance, the context and the tools. In the "Behavior" tab you know instruct your assistant what it should be doing with this.
Instruction
This field allows you to define a generic instruction for your assistant. Usually this can includes things like:
identity/role
task
expectations
rules
Model
Additionally you can select which model should be used by the assistant.
No specific model: Gives users of the assistant the possibility to select the model they would like to use individually, just like in the Zive Chat.
Auto modus: Forces the auto modus and removes the possibility for users of the assistant to switch to a specific model.
One specific model: You define the exact model for the assistant and this will be used in all conversations with the assistant. Users cannot adjust the model.
Tip: Usually it makes sense to test which model delivers the best results and set this model as fixed. This way you can ensure consistent quality answers for all users of the agent.
Steps
Defining steps is optional and in some cases the general instruction might be sufficient, but whenever an assistant should follow a process in a specific order, you should use steps.
Tip: If possible, breaking down complex tasks into steps makes it easier for the assistant to understand and deliver good results.
How to delete an assistant
You can simply delete an assistant that you own after entering the assistant, clicking on the menu icon and selecting delete. You also have this option via the same menu inside the assistant settings.
How to use assistants
Organize your assistants
As a user you can find all assistants available to you when selecting "Assistants" in the navbar on the left.
Favorites: You can mark assistants as favorite by clicking the star icon, which saves them in the section "Your favorite assistants" at the top of the page.
Pinned assistants: For your favorite assistants you can go one step further and also pin them to the navbar for even faster access to your most frequently used assistants.
Work with assistants
You can easily access an assistant by simply clicking on it. In the top right corner you find a button to start a new thread. The welcome message and conversation starters at the top should help you to understand how to use the assistant and submit your initial prompt to start the conversation.
The assistant will perform the steps according to your prompt and the instructions that were defined in the settings and provide you with the desired output.
Attach files to an assistant conversation
There might be use cases that require you to add a relevant file to a conversation with an assistant. You can simply attach content via the icon on the right just like you know from a regular conversation in the Zive Chat.
You can either:
Add files from the company knowledge via searching or browsing
Upload local files from your device
Note: Files attached to a chat do not become available to any other users, even in assistant conversations.
Manage your assistant threads
All your conversations with an assistant are saved to enable you to jump back into a thread whenever you need it. Your most recent threads are displayed on the left side to allow quick access. For a full list just click on "Show all" where you find all your conversation with this assistant. Here you also have the possibility to delete threads from the past.
