Skip to main content
Skills and actions turn an AI Agent from a reply assistant into a support operator that can complete work across your business systems.

​
Core concepts

Instructions

Define the support job, boundaries, tone, and escalation rules.

Skills

Give the agent reusable policies and procedures, such as return eligibility.

Actions

Let the agent retrieve data, reply, update a system, wait, report, or escalate.

Integrations

Connect your shop, ERP, fulfillment, helpdesk, and other business systems.

MCP connections

Extend agents to more than 1,200 available connectors for the systems your support operation uses.

Approval

Keep a person in control of sensitive replies and changes.

​
Connect business systems

Integrations and MCP connections are two ways to give an agent access to live business data and approved operations. Connect the system first, then enable only the actions that the support job requires.

Integrations guide

Connect supported commerce and support systems.

MCP connections

Find and connect additional business tools.
Common customer-support actions include:
  • looking up an order, shipment, return, invoice, or customer
  • updating a shipping address or ticket
  • creating a refund or discount
  • sending a reply, email, or CSAT link
  • waiting before a follow-up
  • routing to a team or person
  • resolving a completed ticket

​
Build a focused agent

1

Write the job in instructions

State what the agent owns, how it should speak, when it must stop, and which cases are out of scope.
2

Add reusable support knowledge

Add skills for policies or procedures that apply across cases, such as return windows or escalation criteria.
3

Connect the required systems

Use an integration or MCP connection for the live data and operations the job needs.
4

Enable only required actions

Keep the action list narrow. Read-only lookups and sensitive changes should be visibly distinct.
5

Set approvals and test

Require approval for high-impact writes, then test success, failure, and escalation cases.

​
Actions have prerequisites

Instructions alone cannot look up an order or hand a ticket to a person. Every capability the agent should use must be enabled as an action, with the right integration selected.
1

Name the work in instructions

Example: look up the Shopify order, reply with the delivery status, hand off when unsure.
2

Enable matching actions

For that job, enable Get order on the Shopify integration, Send reply, and a hand-off action such as Escalate to.
3

Pick the integration account

If several Shopify stores are connected, choose the account the agent should use.
4

Set the decision mode

Keep customer replies and sensitive writes on approval until you trust them. See Human in the loop.
If the instructions say “hand over to the team” but no hand-off action is enabled, the agent cannot actually transfer the ticket. The same applies to order lookups without Get order.
For FAQ agents, enable Search knowledge instead of inventing an integration. Search the knowledge source first, answer only from hits, and hand off when the answer is missing.

​
Hand-off actions

Hand-off actions move the conversation to a human owner.
  • Consult a specialist: This is not a handoff. The current agent stays responsible, asks a focused specialist for evidence or an action, and sends the customer reply itself. Read Subagents.
  • A human: When no specialist fits or judgment is needed, the agent can hand the ticket to a configured person, team, or human queue. This ends the current agent’s responsibility.
An agent only uses the hand-off options you configure and describe in its instructions. It will not pass a ticket around endlessly. Repeated or circular hand-offs stop. Cases that still need attention go to humans. Cases with no needed reply or action can end quietly. A hand-off to a human does not block every AI Agent forever. A later customer message can be matched again. To keep the ticket human-only, narrow or disable matching AI Agent triggers, stop Classic AI auto-reply for the channel, and narrow or disable Workflows with AI prompts. Some cases need no hand-off. A duplicate, an already solved request, or a simple thank-you may end without a reply or human alert when no action is needed. Read Routing and ownership for the full follow-up and hand-off behavior.

​
Approval

Start with approval for:
  • refunds
  • cancellations
  • address updates
  • discounts or replacement shipments
  • other writes to business systems
  • sensitive customer replies
Do not give an agent broad write access. A returns agent should not receive unrelated account, marketing, or catalog actions.

​
Best practices

  • Keep one agent focused on one support outcome.
  • Use current integration data instead of asking customers for information you already have.
  • Add approval before activation and loosen it only after reviewing runs.
  • Explain failures and route the ticket instead of leaving the customer at a dead end.
Action availability does not decide which agent owns the conversation. Configure selection separately in Triggers and filters and Routing and ownership.