Question
You are designing two Microsoft Copilot Studio agents named Agent1 and Agent2. Each agent must meet the following requirements:
Each agent must use a standard model.
Each agent must NOT use generative orchestration.
Agent1 must support simple and short phrases for a given topic.
Agent2 must integrate with Microsoft Dynamics 365 Contact Center voice channel.
You need to recommend language models for the agents.
What should you recommend for each agent? To answer, drag the appropriate language models to the correct agents. Each language model may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Explanation
Both agents use classic orchestration (generative orchestration turned off). Copilot Studio offers three classic language understanding options: NLU, NLU+ and Azure CLU.
Agent1: Natural language understanding (NLU). The original Copilot Studio NLU model suits simpler orchestration needs. You add 5 to 20 short trigger phrases per topic and need no entity annotations, which fits the requirement for simple, short phrases. It is built into Copilot Studio, so it is a standard model.
Agent2: Natural language understanding + (NLU+). NLU+ is available when voice or chat channels are managed with a Dynamics 365 Contact Center license. It is designed for high-accuracy, enterprise-grade agents, and for voice-enabled agents its training data is also used to optimize speech recognition.
Conversational language understanding (CLU) needs an Azure subscription and a custom model that you manage in Azure, so it is not a standard model. Azure OpenAI and Azure Language in Foundry Tools are not classic Copilot Studio NLU options.
