Skip to main content

Introduction Zive Assistant

Learn how to use Zive's AI Assistant to boost your productivity at work.

Updated over 2 weeks ago

Zive allows you to access your company's knowledge as well as your personal work information through an AI-based assistant. We call it the Zive Assistant.

You can ask questions to the Zive Assistant and continue the conversation with it to ask yourself to the right information. Because the Zive Assistant is based on some of the most advanced LLMs out there, you can also use the Zive Assistant as a secure replacement for a public LLM like ChatGPT. For example, you could ask the Zive Assistant to generate content for you on a certain topic, even topics related to your work.

This article focuses on the general functionality of the Zive Assistant. If you're looking for support and orientation how to optimize your usage of the Assistant take a look at our Prompting Guide.

Where to use the Zive Assistant

Starting from your home page

On the home page of your platform you find a prompt input bar at the top through which you can immediately trigger a question or prompt to the Zive Assistant.

Submitting your input will forward you into the full Assistant view, where the answer will be provided.

Starting from the full assistant view

Talking about it, of course, there is also the possibility to start a conversation with the Zive Assistant directly from the main menu. Simply click the "Assistant" button in the main menu on the left and type away.

This is also the best option to engage in more details conversations with the assistant and use more advanced LLM use cases.

Benefit from the Assistant in the search

To provide you with the most accurate answers wherever you are in the platform, the Zive Assistant also triggers in the Zive Search. Whenever you not just search for a keyword but ask a question in the search, a mini version of the Assistant will provide the answer to your question complementing the relevant search results.

How to use the Zive Assistant

Whether you are starting on the home page or in the full view, you find different configuration possibilities below your prompt to adapt the functionality of the assistant to your specific use case.

Understanding and using these configurations when submitting a prompt enables you to exploit the full potential of the Zive Assistant and get the bests results.

Defining the research mode

With the research mode you can tell the assistant exactly whether and where it should search for relevant information and context:

Here is an overview of the different options:

Research mode

Effect

To be used when

None

Limits the Assistant to the trained knowledge of the AI model.

Generic prompt that does not require internal or current external information as context.

Internal

The Assistant will search your internal knowledge available in the platform.

Prompt relates to company knowledge or information to be considered.

Web

The Assistant will search the web to find relevant information.

Prompt requires up to date information from the internet or a web research.

Note: For more detailed information about the research modes take a look at the article "Research modes".

Choosing the AI model

Besides the knowledge mode you can also select the exact LLM that should be used to handle your prompt.

By default the model selection is set to "Auto". In this mode our system automatically identifies the best model by analyzing the prompt. This way you don't have to choose your model manually.

Below every model you find a short description of what the model is good at.

The models available for selection depend on the platform settings defined by your Admins. Find out more about the configuration of available models as an Admin.

Attaching context

By attaching content you can specifically define the context the assistant should consider for its response. You can attach files from different sources:

  • Search for content within Zive

  • Upload local files from your device

Note: Read our dedicated article to get more details about prompt attachments.

Reliability & Limitations

Like always when working with LLMs and generative AI, reliability cannot be 100% guaranteed. That is because LLMs tend to hallucinate or show bias due to the nature of how they function.

Zive has developed a range of highly specialized technologies to ensure that the LLMs stick to the actual knowledge that's available in your workplace. The most important one being the ability to show the Sources that the Zive Assistant has based its answers on, including even the very specific passages within each source.

However, it remains each user's obligation to validate the answers given by the Zive Assistant and possibly check secondary sources such as the Zive Search.

Did this answer your question?