General information
AAI support agentacts as a digital colleague who helps handle incoming cases via phone or chat.
It can answer questions, resolve simple issues, or connect you to human agents if necessary.
The AI support agent can be used in bothresponse groupsandweb chats, and can be connected to aknowledge databaseto retrieve information and answers.
AI support agent in response group
When the AI support agent is enabled, it can respond to incoming calls according to the engagement rules you set.
It can handle all calls, a certain percentage, or only when the response group is closed.
How to activate the AI support agent
1. Open the organization settings
- Click onthe gear wheeland chooseOrganization settings.
- Go toTelephony systemand clickResponse groups.
- Choose itresponse groupwhere you want to activate the AI support agent.
- Scroll down until you see the sectionAI support agent.
2. Enable AI Support Agent
- Click on the menuAI support agent.
- Turn on the sliderEnable AI support agent.
- The AI support agent will receive the pricing plan specified belowOrganization Settings → AI → Licenses and Usage.
3. Choose AI agent
- Under the fieldAI agentyou choose which agent to use in the channel.
4. Set rules of engagement
During the sectionRules of engagementYou specify how often the AI support agent should take calls.
- When open:choose engagement rate between 0% (no calls) and 100% (all calls).Example: Each call has a 50% chance of being handled by the AI agent. This means that it is randomly decided per case.
- When closed:activateEngage all calls when closedif you want the AI agent to respond even when the response group is closed.
5. Enter role description
Write a clear role description that explains what the AI agent will do.
Example:
“Handle incoming calls, ask for customer numbers and try to resolve simple questions. If necessary, transfer to a human agent.”
The role description helps the AI understand its mission in the same way you would instruct a colleague.
6. Set greeting phrase
Enter the phrase that the AI support agent should use when responding.
Example:
“Hi! I'm an AI agent. How can I help you?”
7. Add actions
DuringActionsyou choose how the AI support agent should act during calls.
For example, you can:
- End ongoing callwhen the matter is handled.
- Redirect to human agent when neededwhether the call should be transferred.
Activate the sliderRedirect to human agent when neededif you want to use that feature.
8. Preview the AI support agent
Click onPreview AI support agent via chatto test how the agent behaves before activating it sharply.
9. Save
When you are finished, clickSave.
Your AI support agent is now ready to start handling calls in the response group.
AI support agent in web chat
The AI support agent can be used in web chats to handle customer cases, answer questions, and escalate or move cases as needed.
When enabled, it acts as a digital colleague who is automatically assigned to new chats based on the engagement rules you set.
How to activate the AI support agent in a web chat
1. Open the organization settings
- Click onthe gear wheeland chooseOrganization settings.
- Go toContact Centerand clickChannels.
- Choose itweb chatyou want to activate the AI support agent in.
2. Enable AI Support Agent
- Scroll down to the sectionAI agents.
- ActivateAI support agentby turning on the switch.
- Activation costs1 CC credit.
When the feature is turned on, the AI agent can be assigned as the active agent on new cases.
3. Choose AI agent
Under the fieldAI agentyou choose which AI to use for the web chat.
4. Set rules of engagement
DuringWhen openYou specify how often the AI support agent should take chats.
- 0% means it is not taking any cases.
- 100% means it handles all chats.
Example: Each call has a 50% probability of being handled by the AI agent.
DuringWhen closedcan you activateEngage all chats when closedto allow the AI agent to respond even when the channel is closed.
5. Write a role description
Give the AI support agent a clear role, as if you were instructing a colleague.
Example:
“Always ask for the customer number at the beginning of each chat, try to resolve the issue first and escalate the issue if necessary.”
6. Specify actions
The AI support agent can perform various actions during calls. Here you choose which ones it should have access to:
- End chat– ends chats when the customer is satisfied with the help.
- Escalation of cases– escalates to human colleague if necessary (statusEscalate).
- Resolution of cases– closes cases when the customer is satisfied (statusLoosely).
- Transfer of cases– moves issues to other chats, e.g.Finance group.
You can specify which chats the agent can move cases to duringAllowed coupling receivers.
7. Preview the AI support agent
Click onPreview AI support agent via chatto test your configuration before saving.
8. Save the settings
When everything is ready, clickSave.
Your AI support agent is now active in the selected web chat.
Tip
- Test the AI agent in preview before going live – it makes it easier to see if the role description works as intended.
- Start with a lower engagement level to evaluate agent performance.
- Make sure the AI agent's role description and access to actions match your internal procedures.
Why the role description is crucial
A clear and well-thought-out role description is actually the most important factor in whether the AI agent is successful or not.
It's not just aboutWhatthe agent should do without alsohowit should behave, communicate and prioritize in different situations.
To get really good results, the role description needs to live and develop over time.
Think of it as a document you can constantly adjust based on how the agent actually behaves in real customer dialogues.
Once you have activated the AI agent, take the time to see how it works in practice and then update the role description based on what works well and what could be even better.
Creating an effective AI agent is therefore not a “one and done” project – it requires a little commitment, curiosity and ongoing fine-tuning.
But that is also exactly what makes the difference in how well the agent performs and how well they manage to give your customers a really good experience.