> ## Documentation Index
> Fetch the complete documentation index at: https://docs2.armin.cx/llms.txt
> Use this file to discover all available pages before exploring further.

# Triggers and filters

> Start AI Agents on new tickets or after a delay, then match the right support work.

Triggers decide when Chatarmin CX checks an AI Agent. Filters decide whether the ticket is a match.

## Trigger types

<CardGroup cols={2}>
  <Card title="New ticket" icon="ticket-plus">
    Check the agent when a customer creates a ticket. Filters then decide whether the agent should
    own it.
  </Card>

  <Card title="Delay based" icon="clock">
    Check the agent after a ticket has stayed resolved for the configured time. The ticket must
    still be resolved when the delay ends.
  </Card>
</CardGroup>

Delay-based triggers currently support **Resolved for X**. Use them for CSAT, follow-ups, and reports that should run after a resolved support window.

## Before new matching starts

For an incoming customer message, Chatarmin CX first checks whether an AI Agent or Workflow already owns the conversation. If so, that owner continues before new triggers and filters are considered.

The owner is not simply the latest assignment shown in the Inbox. Assigning a person without replying does not stop the current AI Agent.

After a normal reply, the same agent can continue customer follow-ups for up to 30 days. A human reply stops that agent's follow-up, and the next customer message can be matched again. If the agent is still waiting for customer information, a delay, or approval, a human reply prevents the old work from resuming. That open pause also blocks a fresh AI Agent, so the human team owns the conversation while it remains open.

Read [Routing and ownership](/ai-agents/routing-and-ownership) for examples.

## Matching methods

<CardGroup cols={2}>
  <Card title="Exact filters" icon="list-check">
    Match fixed ticket data such as channel, status, tag, language, team, or integration.
  </Card>

  <Card title="Semantic filter" icon="sparkles">
    Match what the customer means, even when they use different words.
  </Card>
</CardGroup>

Use exact filters to define where the agent is allowed to run. Use a semantic filter to describe the customer request it owns. Most customer-facing agents benefit from both.

## Customer-support examples

* **New ticket + exact filters:** Consider the agent only for German email tickets assigned to the Returns team.
* **New ticket + semantic filter:** Match customers asking where an order is, whether it shipped, or why delivery is late.
* **New ticket + both:** Handle address-change requests only for open Shopify tickets.
* **Delay based:** Send a CSAT follow-up after the ticket has remained resolved for the configured time.

Write semantic filters as short support policies. “Customer asks for the current delivery status of an existing order” is clearer than a list such as “where, tracking, shipped, parcel.”

## Set up a trigger

<Steps>
  <Step title="Choose when to check the agent">
    Use **New ticket** for incoming support or **Delay based** for work after a ticket has stayed
    resolved.
  </Step>

  <Step title="Set exact boundaries">
    Add exact filters for channel, status, integration, language, team, or other fixed ticket data.
  </Step>

  <Step title="Describe the customer request">
    Add a semantic filter for the support request the agent should own. Skip it only when the exact
    conditions alone are intentional.
  </Step>

  <Step title="Test positive and negative cases">
    Test messages that should start the agent, messages for another agent, and ambiguous requests
    that should go to a person or fallback.
  </Step>
</Steps>

## Which agent runs

Only one AI Agent owns the customer conversation at a time. Existing responsible work goes first. A high-confidence macro Workflow can come next. Among eligible AI Agents, the order is exact match, confident meaning-based match, then catch-all. Classic AI is considered only if none of those takes the conversation.

Read the full behavior and examples in [Routing and ownership](/ai-agents/routing-and-ownership).

For ready-to-use trigger patterns, see [AI Agent examples](/ai-agents/examples).