AI Actions allow your AI Voice Agent to take automated actions during live calls by connecting to third-party tools like Shopify, HubSpot, and Zendesk. Once enabled on an integration and assigned to an agent, the agent can autonomously look up or update data in those tools without human intervention.
This article explains what AI Actions are, which actions are available per integration, and how to configure them in two steps: enabling capabilities at the integration level and assigning them to individual agents.
Important: AI Actions with AI Voice Agents are currently only available for Shopify, HubSpot, and Zendesk integrations.
What are AI Actions?
AI Actions are integration-powered capabilities that your AI Voice Agent can invoke during a conversation based on the caller's intent. Examples include looking up an order status, retrieving a contact record, booking a meeting, or opening a support ticket, all without transferring the call or involving an agent.
Each capability must be enabled in two places before it works: first at the integration level, then on the specific AI Voice Agent you want to use it.
Available capabilities by integration
Shopify
| Capability | What it does |
|---|---|
| Get Order | Retrieves order details (status, items, shipping, tracking) using an order number and the caller's phone number or email |
Find more information in the dedicated article "AI Actions: Setting up your AIVA to handle Shopify order status calls".
HubSpot
| Capability | What it does |
|---|---|
| Get Contact | Looks up a contact by phone number, email, or contact ID |
| Get Company | Looks up a company by phone number, email, domain, or company ID |
| Create Contact | Creates a new contact record |
| Update Contact | Updates an existing contact's details |
| Update Company | Updates an existing company's details |
| Create Ticket | Opens a new support ticket |
| Update Ticket | Updates an existing ticket (subject, stage, pipeline) |
| Meeting Availability | Fetches available meeting slots for a given calendar |
| Book Meeting | Books a meeting on behalf of the caller |
Zendesk
| Capability | What it does |
|---|---|
| Search Contact | Looks up a Zendesk user by phone number or email |
| Create Ticket | Creates a new support ticket |
| List Open Tickets | Retrieves all open tickets for a given user |
| Resolve Ticket | Marks a ticket as solved |
Step 1: Enable capabilities on an integration
Before an AI Voice Agent can use a capability, you must enable it at the integration level in the Aircall dashboard.
Steps:
- Go to Aircall Dashboard > Integrations & API
- Open the connected integration you want to configure, for example Shopify, HubSpot, or Zendesk
- Navigate to the AI agent capabilities section within the integration settings
- Toggle on the capabilities you want to make available. Examples by integration:
- Shopify: Order status updates
- HubSpot: Enable Scheduling, Enable Contact details, Enable Company information, Ticket management
- Zendesk: Enable Contact details, Ticket management
Important: All capabilities are off by default. They must be explicitly enabled per integration before they become available to assign to an agent.
Note: For integrations that require OAuth authentication, such as HubSpot, a banner will appear prompting you to reconnect before capabilities can be enabled. The capabilities sync toggle activates only once the OAuth connection is established.
Step 2: Assign capabilities to an AI Voice Agent
Once capabilities are enabled on an integration, you assign them to the specific agents that should use them.
Steps:
- Go to Aircall Dashboard > AI Voice Agents
- Open the agent you want to configure
- In the agent settings, navigate to the Capabilities section under Functional abilities
- Click Add capability to open the capability selector panel
- Select the capabilities you want this agent to use
- Click Save changes
During a live call, the agent will automatically invoke the relevant capability based on the caller's intent and the instructions defined in the agent prompt.
Important: Check for conflicts with existing call logging or integration settings before saving to avoid duplicate actions or unexpected behavior.
Shaping how the agent uses AI Actions
Assigning an AI Action enables it, but defining rules improves accuracy and consistency. You can guide behavior in two places.
Option 1: Conversation Guidelines
Conversation Guidelines live on the agent itself, in the Call script tab of the agent settings. They apply to the whole conversation. This is the right place for rules that span more than one AI Action, govern the overall flow of the call, or describe how the agent should behave regardless of which action it ends up using.
Use Conversation Guidelines when you want to:
- Sequence multiple AI Actions: "First identify the caller with Get Contact, Then use the requester id from Search Contact look up their open tickets with List Open Tickets, then ask which one they want to discuss."
- Set ground rules for the whole call: "Always confirm the caller’s name before sharing any account detail."
- Describe a fallback path: "If you cannot identify the caller after two attempts, transfer to the support team."
- Coordinate between AI Actions and call transfer rules: "If the caller asks about billing, do not use any AI Action - transfer to the billing team instead."
Option 2: Custom instructions
Custom instructions live on the AI Action itself, inside the Advanced settings of that specific action on a specific agent. They apply only when that one action is being used. This is the right place for rules that are tightly scoped to a single action - when to reach for it, how to react to the specific fields that come back, and what to do for the failure modes of that action.
Use custom instructions when you want to:
- Refine the trigger for one specific AI Action: "Use Get Order Details when the caller asks about delivery, tracking, or where their package is - but not for refunds.")
- Branch on a specific return value: "If financial_status is PAID, reassure the caller. If it is PENDING, tell them to check their email for a payment issue.")
- Tighten the verification threshold for that one action: "Require both email and phone before sharing any order detail."
- Handle the not-found case: "If the order cannot be found after one attempt, offer to transfer to the support team."
Choosing the right option
Both options accept the same plain-English style. Treat each line as a rule for the agent. Be specific about the trigger, the data, and the desired response. Avoid contradictions - if two rules disagree, the agent will pick one and ignore the other.
| Conversation Guidelines | Custom instructions |
|---|---|
| Apply to the whole agent | Apply to one AI Action |
| Best for multi-step flows | Best for single-action tuning |
| Control overall call behavior | Control specific action logic |
| Edited once for all calls | Configured per action per agent |
Important: Define each rule in only one place. Duplicating rules across both areas can create inconsistencies and make debugging difficult.
Testing your AI Actions
Test your setup in two stages before going live.
1. Test the action
Use the Testing tab in the integration:
- Open the MCP Playground
- Select an action
- Enter parameters
- Click Execute
This verifies connectivity and response structure.
2. Test the agent
Use Test call in agent settings:
- Validate real call behavior
- Test different scenarios such as success, alternative outcomes, and failures
- Confirm multi-action sequences
Note: Test calls consume AI Voice Agent minutes and may create real records. Use test environments or dummy data when possible.
Common issues include:
- Conflicting rules
- Poorly defined triggers
- Incorrect field references
Billing
AI Actions are included at no additional cost. Capability invocations count against the AI Voice Agent minutes already included in your plan. There is no separate billing line and no per-invocation charge.
If your AI Voice Agent minutes are exhausted, the agent will no longer handle calls and will not be able to invoke capabilities until minutes are replenished.
FAQs:
Do I need to configure capabilities separately for each AI Voice Agent?
Yes. Capabilities must be enabled at the integration level first, then assigned individually to each agent that should use them. Enabling a capability on an integration does not automatically assign it to any agent.
Can I enable capabilities for some agents but not others?
Yes. Each agent has its own AI Actions section. You can assign different combinations of capabilities to different agents depending on their purpose.
What happens if a capability conflicts with my call logging settings?
A warning banner will appear in both the integration settings and the affected agent configuration. Review the conflict and resolve it before saving. Keeping both active may cause unexpected behavior.
Are AI Actions available on all Aircall plans?
AI Actions are included within your existing AI Voice Agent minutes. No additional SKU or add-on is required. Confirm with your account manager if you are unsure whether AI Voice Agent minutes are included in your plan.
What is the difference between enabling a capability on an integration and assigning it to an agent?
Enabling a capability on an integration makes it available in the system. Assigning it to an agent allows that specific agent to use the capability during calls. Both steps are required.
Aircall Status
Help logging in