Automate intent discovery and resolution with Customer Intent Agent in Dynamics 365 Contact Centre

Automate intent discovery and resolution with Customer Intent Agent (A specialized AI agent that proactively identifies emerging customer needs and builds the necessary logic to resolve them).

Real-time User Journey

This journey highlights how the agent transitions from “Discovery” to “Resolution” without manual administrative work:

1. Passive Discovery: The Customer Intent Agent continuously scans thousands of historical transcripts and real-time interactions across voice and chat.
2. Pattern Identification: The AI identifies a new, rising trend: many customers are asking about “Loyalty Point Expiration” following a recent policy change—a category that didn’t exist in the current routing rules.
3. Intent Proposal: The agent alerts the supervisor: “I’ve discovered a new intent: ‘Loyalty Inquiry.’ Would you like me to create a resolution path for this?”
4. Autonomous Training: Upon approval, the agent automatically maps relevant phrases to this new intent and suggests the best knowledge articles or automated bot topics to address it.
5. Closing the Loop: The next customer who asks, “When do my points vanish?” is immediately recognized by the new intent and routed to the correct automated resolution, bypassing the general “Other” queue.

Step-by-Step: How to Enable This Feature

The Customer Intent Agent is part of the Agentic Contact Center suite. Follow these steps to activate it:

• Step 1: Admin Center Access

Sign in to the Contact Center admin center or Customer Service admin center.

• Step 2: Access the Agent Hub

Navigate to Operations > Agent Hub. This is the centralized control center for all autonomous agents.

• Step 3: Enable Intent Discovery

Locate the Customer Intent Agent card and select Manage. Toggle the Discovery setting to On. This allows the agent to begin analyzing historical and live data.

• Step 4: Configure Data Sources

Specify which channels (Voice, Chat, Email) the agent should monitor. You can also point it toward specific historical timeframes (e.g., the last 30 days) to find recent trends.

• Step 5: Set Approval Workflows

Choose between Semi-autonomous (the agent suggests new intents for your approval) or Fully autonomous (the agent creates and applies the intent logic automatically). Microsoft recommends Semi-autonomous for the first 30 days.

• Step 6: Link to Copilot Studio

Ensure the agent is connected to your Copilot Studio environment so it can automatically suggest or create new bot topics based on the discovered intents.

Infographic: The Customer Intent Agent Lifecycle

Feature	Traditional Manual Discovery	Customer Intent Agent
Speed	Weekly or monthly manual audits.	Real-time continuous monitoring.
Accuracy	Subject to human bias/sampling.	Data-driven across 100% of transcripts.
Implementation	Manual rule-building & bot training.	Auto-suggests phrases and resolution paths.
Scalability	Hard to track multiple minor trends.	Captures long-tail and emerging issues instantly.
Outcome	Reactive updates to routing.	Proactive optimization of the service journey.

References

Automate intent discovery and resolution with Customer Intent Agent