Skip to main content
AI Agents automate customer support tickets end to end. They understand the request, use current business data, take approved actions, and keep the customer informed until the ticket is resolved or handed to a person.

​
One conversation owner

Think of a ticket like a relay baton. One AI Agent or Workflow owns the customer conversation at a time. For up to 30 days after a normal AI reply, the same agent normally handles the customer’s follow-up with context. It can also hand the conversation to one suitable specialist or a human. After the agent finishes normal work, a human reply stops that agent’s follow-up. A later message can be matched again. If the agent is still paused for customer information, a delay, or approval, the human reply prevents it from resuming, but the open pause also blocks a fresh AI Agent. Read Routing and ownership for the full behavior.

​
What an AI Agent can do

An AI Agent can:
  • understand the customer’s intent and conversation history
  • retrieve live order, shipment, return, and customer data
  • answer questions and update connected systems
  • wait, follow up, and collect feedback
  • route or escalate sensitive and exceptional cases
  • resolve completed tickets
  • prepare and send scheduled support reports
Channels bring conversations into the Inbox. Integrations and more than 1,200 MCP connections give agents access to the business systems needed to complete the job. Ask Torben helps you create, test, diagnose, and improve each agent.

​
Common support jobs

Order tracking

Answer WISMO questions with live shipping status.

FAQs

Reply from your knowledge base and route uncertain cases.

Returns and refunds

Check policy and order data, then process or escalate.

Address updates

Change delivery details while the order is still editable.

Discount rescue

Detect an at-risk customer and send an approved offer.

CSAT and reporting

Follow up after support and share recurring reports.

​
Start here

Getting started

Create, test, and activate your first focused AI Agent.

Triggers and filters

Start an agent from an exact match, customer intent, or a delay.

Routing and ownership

Understand which automation owns the customer conversation.

Skills and actions

Connect knowledge, business data, actions, and approvals.

Testing and runs

Validate behavior and inspect every execution.

Examples

Launch from current customer-support templates.

​
Open AI Agents

AI Agents overview

Create agents and review support automation at a glance.

Run history

Inspect live and test executions across agents.

Suggestions

Find recurring support topics worth automating.

MCP connections

Connect more business systems to your agents.
For new support automation, start with AI Agents. Rules remain useful for exact, simple if/then changes. Classic AI is considered only when no existing work, macro Workflow, or AI Agent takes the conversation. See Routing and ownership.