The digital virtual agent focuses on text-based interactions, with configuration and usage centered on the dialogue logic itself.
1. Creation & Configuration
Unlike voice agents, digital agents do not require configuration for voice (TTS) or speech recognition (ASR).
Path: AI Center → Digital Virtual Agent → Create New
-
Basic Information:
-
Name: Assign a name to your digital agent, e.g., “Pre-sales Consulting Bot” or “WhatsApp After-sales Agent.”
-
Conversation Context: Define the agent’s role, background, and overall objectives. This is identical to the setup for voice agents and is crucial for defining the AI’s core capabilities.
-
AI Engine / Model Version: Select the large language model that powers the AI’s reasoning, same as in voice agent configuration.
-
Description: Add notes on the agent’s intended purpose.
-
2. Workflow Design
Workflow design for digital agents is identical to the “Do (LLM + Workflow)” setup for voice virtual agents. You can reuse all knowledge and operations from the previous chapter, including flowcharts and nodes (e.g., intelligent dialogue, conditional branching, variable modification).
Path: After creating a digital agent, enter the configuration page. The default tab displays the flowchart.
-
Triggers (Trigger):
Digital agents are typically used to handle inbound messages. After the start node, you can connect a trigger node.-
You can define one or more keywords. When a user’s first message contains these keywords, the process will be activated.
-
If no keywords are defined, all new conversations sent to this channel will be handled by the digital agent.
-
3. Testing
Once the workflow is designed, conduct thorough text testing to ensure the logic behaves as expected.
Path: In the digital agent editing page, click the Test button in the top right corner.
-
Test Interface: A chat window where you can input text to simulate user conversations.
-
Dialogue Flow: Verify whether the agent’s replies are accurate and natural.
-
Debug Mode: By clicking the debug icon, you can view real-time flow transitions and variable changes, which is useful for troubleshooting logic errors.
4. Channel Deployment & Management
After configuration and testing, the digital agent must be deployed to business channels to go live.
Example: WhatsApp Channel
Path: Management → Digital → Channel Settings → WhatsApp
-
Enable AI Agent:
-
Locate the account where you want to deploy the agent.
-
Switch on Enable AI Agent for this account.
-
From the dropdown menu, select the digital agent you just created and tested.
-
Note: Once enabled, this account’s conversation flow will be handled by the digital virtual agent, replacing the original auto-reply process.
-
-
Start Service:
After saving settings, all new messages sent to this WhatsApp account will be handled first by the digital virtual agent (provided they match the defined trigger).-
If the AI agent cannot resolve the issue or triggers the “human handoff” logic, the conversation will be routed to a human agent according to preset rules.
-
5. Viewing Communication Records
Similar to voice agents, all conversations between digital agents and users can be monitored and analyzed.
Path: Reports → AI Conversations
- Here you can filter and view sessions handled by AI.
- Complete conversation record, AI intent recognition tags, customer information, and more are recorded in detail for subsequent analysis and optimization.