Creating an Expert

Adding an Expert

Experts are task-focused AI agents, that act as virtual employees to respond to specific types of enquires using your organization’s curated content. For example, a marketing expert might have access to all the company marketing material and competitive information, while a developer expert might have access to all the CTERA SDK and its examples.

Expert settings include the following:

Workers Configuration
Embedding Configuration
Model Configuration
Chat Configuration

To create an expert:

Click your avatar at the bottom of the side panel to display additional options.
Click Administration.

The Content Services administrator creates the datasets that you can use to create an expert. You can display the available datasets by clicking Datasets in the navigation pane.

You can display the files that are in that dataset by clicking Files in the navigation pane.
Click Experts in the navigation pane.
All the experts that you have access to are listed.
- Click My Experts to display the experts that you have created.
Or
- Click Shared With Me to display the experts that have been shared with you to use.
Click New Expert.
Enter the expert details:
Expert Name – A name to identify the expert.
Expert Subtitle – A short description of the expert.
Upload a jpeg or png file to use as the expert avatar.
Select the expert owner from the drop-down list and collaborators for this expert, from the drop-down list.
If you specify any collaborators, only these users will have access to the expert.
Slide Set as Public Expert on if you want this expert to be available publicly.
Slide Set as Default Expert on if you want this expert to be the default expert for all users.
Under Expert Settings specify the instructions to manage the expert.
Select the LLM to use for this expert in the LLM Model field.
Select the datasets to use for this expert in the Datasets field.
Slide the tools on under Expert Tools that will be used with this expert, for example Semantic Search and Image Generator.
Optionally , select an MCP Server from the MCP Servers list.
Click Save