Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
Applies to: Dynamics 365 Contact Center—embedded, Dynamics 365 Contact Center—standalone, and Dynamics 365 Customer Service
Note
Copilot Studio bot is renamed as Copilot agent (agent or AI agent). Human agent is now renamed as customer service representative (service representative or representative). You might come across references to the old and new terms while we update the product UI, documentation, and training content.
An AI agent is a program that provides automated responses in a conversational manner to a customer. It can also help resolve customer queries by using case deflection. An agent can also collect basic information from a customer and then provide it to a customer service representative (service representative or representative) to work further on the issue raised by the customer.
An agent eases the load on your customer service service representatives by handling basic queries. This saves your representatives' time so they can work on more complex issues. You can configure your agents to escalate a query to a human representative as required, or when requested by the customer.
In Omnichannel for Customer Service, you can integrate agents created in both Azure and Copilot Studio to perform tasks like starting a conversation with the customer, providing automated responses, and then transferring the conversation to a service representative, as required.
Integrate Azure and Copilot agents
When you integrate agents with Omnichannel for Customer Service, you get the following capabilities:
- Seamlessly integrate your agents with chat and social channels without needing to add channel-specific code in the agent.
- Transfer chat conversations from agents to representatives, together with the full context of the conversation.
- Analyze the agent transcript that's available in Microsoft Dataverse after the conversation is completed.
- Configure routing rules to selectively route incoming requests to agents based on context, such as issue type or customer type. For example, you can route low-complexity issues, or route the conversation to a sales or support agent based on the web browsing history of the customer.
- Monitor agent conversations in real time by using the supervisor dashboard, which includes details such as customer sentiment.
- Use historical dashboards to get insights into the effectiveness of the agents through metrics such as resolution rate, escalation rate, resolution time, escalation time, and average sentiment.
- Configure post-call surveys to measure customer satisfaction.
Related information
Bot sessions and licensing
Integrate an Azure bot
Integrate Copilot Studio bot
Configure Copilot Studio bot for voice