Skip to main content

FAQs: Agent Copilot

Why do summaries fail to generate?

Agents may receive the message Summary Not Generated. Please enter summary manually from time to time. The most common reasons for this error are the following.

  • The interaction is too short.
  • The interaction is transferred from an agent who does not have an Agent Copilot license.
  • The number of summaries being generated per minute exceeds the current limit for the organization.
  • The voice conversation is very long or the digital interaction contains an extraordinarily high number of characters.

In these cases, an agent can still enter the summary manually.

How does AI generation work?

Genesys Agent Copilot uses Retrieval-Augmented Generation (RAG) to generate auto-suggested answers. Queries to the RAG system are customer turns. The retrieval engine uses a hybrid search methodology, which combines keyword and semantic searches to retrieve the most relevant chunks from the indexed Knowledge Base. The generation engine consumes the retrieved chunks along with the query, and prompts an LLM to generate an answer along with accurate citations. For more information, see .

How can I improve the frequency of AI-generated answers for auto-suggested knowledge?

Create well-structured articles separated into paragraphs. Aim for semantically coherent paragraphs that are around 200 words long. This allows for more precise retrieval and accurate generation. For more information, see .

Do summaries generated by Agent Copilot persist longer than 10 days?

If you have the Genesys Cloud CX 3, Genesys Cloud CX 4, or a Genesys Cloud CX 1 or Genesys Cloud CX 2 with Genesys Cloud CX 1 WEM Add-on II, Genesys Cloud CX 2 WEM Add-on I, or Genesys Cloud Analytics Add-on license, you can see see summaries and insights in the Interaction Details view. To view this information, enable AI Insights in speech and text analytics Program settings for a set of Agent Copilot queues and flows. For more information, see .

After you enable the AI Insights setting, Genesys Cloud stores the agent summaries that Agent Copilot generates longer than 10 days and retains them for as long as the interaction recording is stored.

You can also access the summaries via these Speech and Text Analytics APIs.

Can I see summaries and insights generated by Agent Copilot in the interaction details view?

If you have the Genesys Cloud CX 3, Genesys Cloud CX 4, or a Genesys Cloud CX 1 or Genesys Cloud CX 2 with Genesys Cloud CX 1 WEM Add-on II, Genesys Cloud CX 2 WEM Add-on I, or Genesys Cloud Analytics Add-on license, you can see see summaries and insights in the Interaction Details view. To view this information, enable AI Insights in speech and text analytics Program settings for a set of Agent Copilot queues and flows. For more information, see .

If an interaction is already summarized by Agent Copilot, will I be charged again for Virtual Supervisor’s AI Summary and Insights?

No. If Agent Copilot is enabled for an interaction and already generates a summary, Virtual Supervisor’s AI Summary & Insights uses that same summary without generating additional cost. You are not billed twice for the same interaction.

How can I suppress segment filtering on knowledge articles for Agent Copilot?

Genesys Cloud supports an API that disables segment-based filtering for Genesys Cloud Knowledge Base content when accessed via Agent Copilot. This API provides automatic suggestions, manual search, autocomplete, and answer highlighting. AI-generated responses surface knowledge regardless of segmentation filters. For more information, see The Genesys Cloud Developer Center.

Is there a charge to generate Supervisor Copilot summary for interactions that were already summarized by Agent Copilot?

Genesys Cloud will not double-bill for summaries when an interaction has already been summarized by Agent Copilot, even if the AI Insights toggle is also enabled and a conversation summary is generated.

For more information, see .

Do the existing evaluation limits apply to AI Scoring driven evaluations? 

Yes, agent and evaluation centered evaluation daily limits (50 per day), apply to both regular and AI driven evaluations. The limit can be increased on an individual customer basis to either 100 or 200 per day, by creating a customer care ticket with this request.

Is STA (Speech and Text Analytics) required for AI Scoring? 

Yes, if you intend to use AI scoring to evaluate calls. AI Scoring requires interactions to be transcribed.