Genesys Agent Assist

Monitor conversations between the customer and agent to surface contextually relevant knowledge and FAQs.

What's the challenge?

Many customers prefer to use self-service options. But when they need to speak to someone (via voice or chat), they expect that person to know all about their journey and how best to help them in real time.

What's the solution?

Provide live transcripts of the voice conversation, and relevant real-time knowledge suggestions on the agent’s omnichannel desktop.

Use case overview

Story and business context

A positive customer experience relies on the ability of the company or provider to answer a customer’s request, provide excellent service, and deliver on the requested outcome. Contact centers are often the single point of contact for customers, and it is critical that agents properly and effectively handle these interactions. Agents must navigate knowledge and FAQs to find answers and resolve customer inquiries – which takes time that could be better spent on activities that improve customer service or sales outcome.

With Agent Assist, companies can rely on the power of artificial intelligence (AI) to monitor and analyze the conversation and then deliver contextual, relevant information drawn from a knowledge base to provide relevant suggestions to the agent. The agent spends time assisting the customer based on the suggested results, rather than digging for information. To improve the knowledge base for future use, an agent may verify whether the suggestions that Genesys Agent Assist AI returns are relevant.

Genesys offers Agent Assist as a native AI capability fully integrated into Genesys Cloud CX. Genesys also enables customers to use Google CCAI transcription and knowledge services for voice-based Agent Assist as an alternative

Use case benefits

Benefit Explanation
Improved Employee Satisfaction Agents tackle more complex business inquiries with AI assistance.
Improved Employee Utilization A constantly-evolving knowledge base trains agents in real time.
Improved First Contact Resolution Present relevant suggestions in real-time to help the agent resolve the caller's inquiry.
Reduced Handle Time By empowering agents to more effectively provide answers, callers enjoy a quicker, more positive experience.


During a call or digital interaction between a customer and an agent, to assist the agent, Genesys Cloud Agent Assist presents relevant, real-time suggestions to the agent in their desktop. Agent assist provides contextually relevant knowledge suggestions, such as answers to frequently asked questions to the agent in real time. The knowledge empowers the agent, provides the right information at the right time, and enables the agent to provide better support to a end-customer.

Use case definition

Business flow

1.Genesys connects the user to the live agent.

2.The agent sees the context (for example bot intents and slots) of the users journey in the agent desktop.

3.Genesys Agent Assist monitors the conversation.

4.During the voice conversation, the following happens:

For Voice Interactions:

  • Real-time audio of the voice interaction is streamed to Genesys Transcription service.
  • Agent Assist displays the real-time transcription of the voice call.
  • Agent Assist service returns real-time knowledge suggestions.
  • The suggested content is displayed to the agent automatically in a live stream of suggestions during the conversation.

For Digital Interactions:

  • Agent Assist service returns real-time knowledge suggestions.
  • The suggested content is displayed to the agent automatically in a live stream of suggestions during the conversation.

5.The agent can do the following with the live stream of suggestions:

  • Click to expand the suggested content to read more (BL1).
  • For Voice: Read the suggested content directly to the customer or use it to assist with the interaction (BL2).
  • For Digital: one click copy the content to the chat window.

6.The agent can rate (upvote/downvote) to improve the AI suggestions model over time. The more that Agent Assist is used and content rated by agents, the better the suggestions will be in the future. (BL3, BL4).

Business and distribution logic

Business Logic

BL1: Review knowledge: The agent performs a high-level assessment to ensure the information returned from Agent Assist is appropriate and relevant to the current conversation.

BL2: Leverage knowledge: The agent communicates relevant information to the end-customer, or they use the information to perform the required “back-end” actions to resolve the customer issue.

BL3: Rate knowledge: Agent assist may provide an agent with multiple pieces of information during the interaction. Agents should rate the information using the thumbs up / thumbs down buttons to verify as relevant or irrelevant.

BL4: Resolve issue or continue conversation: If the end-customer issue is not adequately resolved, the agent continues the conversation with the end-customer to trigger Agent Assist to surface additional information. If Agent Assist is unable to provide appropriate information to resolve the end-customers issue, Agents should follow their corporate escalation policy to ensure that expectations are fulfilled.

Distribution Logic

Since the end-customer is already speaking with an agent in real time, any subsequent call steering is likely to be manually directed by the agent.

User interface & reporting

Agent UI



Real-time Reporting

The knowledge dashboard for Genesys Agent Assist gives overview about knowledge base article activities. Genesys Agent Assist metrics and reporting provides insight about presented, opened and copied articles. For more information, see

Historical Reporting

In the knowledge optimizer dashboard, you can analyze the effectiveness of your knowledge base. In this view, you can see the following metrics:

  • All queries in a specific time frame and the breakdown, in percentages, of answered and unanswered queries.
  • All answered queries in a specific time frame and the breakdown, in percentages, of the application from which the conversation originated.
  • All unanswered queries in a specific time frame and the breakdown, in percentages, of the application from which the conversation originated.
  • Top 20 articles and the frequency in which an article appeared in a conversation.
  • Top 20 answered queries and the frequency in which each answered query appeared in a conversation.
  • Top 20 unanswered queries and the frequency in which each unanswered query appeared in a conversation.


Customer-facing considerations


All of the following required: At least one of the following required: Optional Exceptions

General assumptions

Customers and/or Genesys Professional Services are responsible for managing and uploading their own knowledge base content into Genesys Knowledge Workbench to be used by Agent Assist.

Customer responsibilities


Related documentation

Document version

 V 2.0.0 last updated March 14, 2023