Connect an agentic virtual agent to a knowledge fabric configuration

AI-generated summary

Genesys Cloud's AI Studio platform delivers comprehensive virtual agent capabilities through its intuitive interface, accessed via Admin > AI Studio > Guides. The system employs core commands like Say, Ask, Ask and Confirm, and Call, supporting multi-language functionality while maintaining English command syntax. Essential integration features include variable implementation, conditional logic, navigation commands, and knowledge configuration connections, all working seamlessly with Architect and digital bot flows. Technical implementation requires Virtual Agent organization enablement, proper permissions, and adherence to formatting rules for variables, step names, and Boolean conditions. The platform provides automatic syntax validation during saving and publishing processes, along with guide duplication and deletion options. Knowledge configuration setup involves specific naming conventions, detailed descriptions, and appropriate knowledge source selection. Domain-specific knowledge base names and clear configuration descriptions are essential, with pre-instructions establishing usage conditions and content scope. The system supports query formatting requirements, content limitations, and multiple pre-instructions for comprehensive knowledge usage guidelines. The profile interface offers sections for Agent, Tools, Knowledge, Configuration, and Guardrails, featuring a preview widget for testing. While profiles can be saved with incomplete sections, publishing requires all sections to be complete. The platform integrates with SharePoint, supports multiple languages, and includes a final review step in the tab for parameter examination before publishing virtual agent flows

Series: Create an agentic virtual agent

Previous suggested step: Set up tools for an agentic virtual agent

Feature coming soon: Agentic virtual agents

PrerequisitesClick to expand

Knowledge configuration supplies relevant data sources and more context for your agentic virtual agents during conversations.

Connect to knowledge configuration

Click Menu > Orchestration > AI Studio > Agentic Virtual Agents.
(Optional) To search for a specific agent, start typing the name of the agent in the search box. As you type, the matching agents are shown.
To open an AI agent, click the agent’s tile. The Agent profile view opens.
Select the Knowledge tab.
In the Name field, enter a meaningful name. For example, “search_banking_faq_knowledge_base”.
In the Description field, enter a high-level summary about the knowledge connection.
In the Knowledge section, select a knowledge configuration from the Choose your knowledge configuration list. A preview tile of the selected knowledge configuration appears showing its connected sources and sync information. For more information about creating a knowledge configuration, see [link to fabric article].
Click Next to proceed to the Input tab.

Knowledge configuration name examplesClick to expand

Do / Don’t	Example	Explanation
	search_banking_faq_knowledge_base	It explains that it is a knowledge base but also that it is a banking FAQ source.
	search_mortgage_and_general_loan_knowledge_base	It informs the model that the knowledge base contains information about mortgage and general loan questions.
	search payment and transaction knowledge base	This is domain-specific information about what the knowledge base covers. The model can understand its purpose and can differentiate it from other tools.
	search_knowledge	It is too vague.
	knowledge tool that gets information	It is vague and it is not domain-specific. It does not give any relevant information.

Knowledge configuration description examplesClick to expand

Do / Don’t	Example	Explanation
	This function issues the search query against a knowledge base with answers to consumer banking FAQs.	Explains what kind of knowledge base that it is at a high level.
	This is a knowledge search tool.	Does not tell the agent when to call it and how to use it. It is too vague.

Set up input conditions

Under Pre-instructions in the Input tab, click Add to add any conditions that must be met before this knowledge connection is used by the agent. For example, “The knowledge configuration contains banking FAQs covering account management, online banking, and mobile banking”.
Add as many pre-instructions as needed for the intended knowledge usage.
Click Next to proceed to the Output tab.

Knowledge pre-instruction examplesClick to expand

Good pre-instructions answer these questions:

Why should the agent call the knowledge configuration?
When should the agent call the knowledge configuration?
What should the agent do before it calls the knowledge configuration?

Do / Don’t	Example	Explanation
	The knowledge base contains banking FAQs covering account management, online banking, mobile banking, security and fraud, loans and credit, deposits and withdrawals, fees and charges, cards and payments, investment services, and customer care.	Gives more context about what is in the knowledge base.
	If the user is having trouble authenticating (for instance, if they cannot remember their password or email), or if their accounts are not as expected, do not call the FAQ, as it does not contain information about those issues.	Includes what is not in the knowledge base. Especially for cases where the agent gets confused. For example, mortgage loan information only.
	Always translate the query argument into English before using this search function. The query must be in the form of a question, for example: “How long does it take for transfers between accounts to settle?” There is no way to call this function with the query argument in a different language.	Specific instructions that tell the agent what to do beforehand (for example, if you know that the knowledge is in a different language, you can adjust the data sent by the model).
	This knowledge tool has all the information about the banking procedures.	It is too vague and high level.

Set up output delivery

Under Outcome Instructions in the Output tab, add the following response messages:
- No result response: The message (or a similar message) that the agent sends if the agent finds no matching result.
- Follow-up response: The message (or a similar message) that the agent sends as a follow-up after sending the matched result.
Click Next to proceed to the Summary tab.

Note: The outcome instructions are not mandatory requirements but recommendations for the agent. They are not delivered verbatim but are paraphrased based on the conversational context.

Review and save the configuration

Get a consolidated view of the entire knowledge configuration, identify any improvement areas, and tweak the settings before saving the configuration.

In the Summary tab, review all the parameters of the knowledge configuration.
Click Edit any of the tiles if you want to edit the parameters.
Click Create to save the knowledge configuration.

Note: Ensure that the topics and questions this knowledge configuration contains are covered in the description (scope) of the agent’s role and guidelines.

Navigating the agentic virtual agent profile

The profile contains the following sections and a preview widget:

Show meClick to expand

You can switch to any of the sections of the agentic virtual agent while creating a new agent, editing an existing agent, or viewing an agent. Any incomplete section is indicated by the icon preceding the section name. You can save an agent with an incomplete section but you cannot publish the agent until all sections are complete.

After you have completed all necessary sections of the agent setup, you can click Publish to publish the flow.

[NEXT] Was this article helpful?

Get user feedback about articles.

Connect an agentic virtual agent to a knowledge fabric configuration View summary