Using Built-in Actions

Moveworks provides built-in actions for common platform operations — user lookups, notifications, approvals, and LLM generation. These are ready to use without creating connectors or HTTP actions.

When you want to use a built-in action in your Compound Action, use mw.{{action_name}} as your action_name. For example:

1
- action:
2
    action_name: mw.get_user_by_email
3
    output_key: user_result
4
    input_args:
5
      user_email: meta_info.user.email_addr

Action Reference

get_user_by_email

Retrieve a single user record by email address. Returns all user attributes including custom attributes.

Action Name: mw.get_user_by_email

Input Parameters:

Example:

1
- action:
2
    output_key: user_result
3
    action_name: mw.get_user_by_email
4
    input_args:
5
      user_email: meta_info.user.email_addr

Response Schema:

1
{
2
  "user": {
3
    "full_name": "John Doe",
4
    "email_addr": "john.doe@moveworks.ai",
5
    "record_id": "10769610738892443",
6
    "department": "Engineering",
7
    ...
8
  }
9
}

Reference: data.user_result.user.email_addr, data.user_result.user.full_name, etc.

You can find the full list of user fields in our User Attribute Reference.

batch_get_users_by_email

Retrieve multiple users by email in a single call. Use this when you need to resolve several users (e.g., an approver and a requester).

Action Name: mw.batch_get_users_by_email

Input Parameters:

Example:

1
- action:
2
    output_key: target_users
3
    action_name: mw.batch_get_users_by_email
4
    input_args:
5
      user_emails:
6
        - data.manager_email
7
        - data.employee_email

Response Schema:

1
{
2
  "user_records": [
3
    {
4
      "lookup_id": "12345",
5
      "user": {
6
        "full_name": "John Doe",
7
        "email_addr": "john.doe@moveworks.ai",
8
        "record_id": "10769610738892443",
9
        ...
10
      }
11
    },
12
    {
13
      "lookup_id": "67890",
14
      "user": {
15
        "full_name": "Jane Smith",
16
        "email_addr": "jane.smith@moveworks.ai",
17
        "record_id": "10769610738892444",
18
        ...
19
      }
20
    }
21
  ]
22
}

Reference: data.target_users.user_records[0].user for the first user, data.target_users.user_records[-1].user for the last.

You can find the full list of user fields in our User Attribute Reference.

create_generic_approval_request

Create a Moveworks in-bot approval request. The compound action pauses execution until the approval is answered (up to 30 days).

Action Name: mw.create_generic_approval_request

Input Parameters:

Example:

1
- action:
2
    output_key: approval_result
3
    action_name: mw.create_generic_approval_request
4
    input_args:
5
      title: '''Access to Coupa Request'''
6
      approval_details: '''Need access to Coupa for procurement workflow'''
7
      approvers:
8
        - data.manager_user.user
9
      users_requested_for:
10
        - data.requesting_user.user
11
    progress_updates:
12
      on_pending: Sending approval request...
13
      on_complete: Approval received.

Response Schema (Approved):

1
{
2
  "status": "APPROVED",
3
  "approved_by": [
4
    {
5
      "full_name": "John Doe",
6
      "record_id": "10769610738892443",
7
      "email_addr": "john@moveworks.ai",
8
      "comment": "Looks good, approved."
9
    }
10
  ],
11
  "state": {
12
    "initial_status": "PROCESSING",
13
    "status": {
14
      "john@moveworks.ai": "APPROVED"
15
    }
16
  }
17
}

Response Schema (Denied):

1
{
2
  "status": "DENIED",
3
  "denied_by": [
4
    {
5
      "full_name": "John Doe",
6
      "record_id": "10769610738892443",
7
      "email_addr": "john@moveworks.ai",
8
      "comment": "Budget not available for Q2."
9
    }
10
  ],
11
  "state": {
12
    "initial_status": "PROCESSING",
13
    "status": {
14
      "john@moveworks.ai": "DENIED"
15
    }
16
  }
17
}

Reference: data.approval_result.status returns "APPROVED" or "DENIED" (uppercase).

To access the approver/denier’s comment (e.g., a denial justification):

1
# Access the denial comment
2
message: data.approval_result.denied_by[0].comment
3
4
# Access an approval comment
5
message: data.approval_result.approved_by[0].comment

batch_send_plaintext_chat_notification

Send a chat notification to one or more users. Use with batch_get_users_by_email to resolve user record IDs first.

Action Name: mw.batch_send_plaintext_chat_notification

Input Parameters:

Example:

1
- action:
2
    output_key: target_users
3
    action_name: mw.batch_get_users_by_email
4
    input_args:
5
      user_emails:
6
        - '''alice@example.com'''
7
        - '''bob@example.com'''
8
- action:
9
    action_name: mw.batch_send_plaintext_chat_notification
10
    output_key: notification_result
11
    input_args:
12
      notifications:
13
        MAP():
14
          items: data.target_users.user_records
15
          converter:
16
            user_record_id: item.user.record_id
17
            message: '''Please complete your quarterly review.'''

Response Schema:

1
{
2
  "user_notification_tracker_details": [
3
    {
4
      "notification_tracker_uuid": "abc-123-def"
5
    }
6
  ]
7
}

generate_text_action

Generate free-form text output using an LLM. Use for summarization, classification, formatting, and other text generation tasks.

Action Name: mw.generate_text_action

Input Parameters:

Example:

1
- action:
2
    action_name: mw.generate_text_action
3
    output_key: summary_result
4
    input_args:
5
      system_prompt: '''Summarize the following text in 2-3 sentences.'''
6
      user_input: data.article_content
7
      model: '''gpt-4o-mini'''
8
      temperature: '0.7'

Response: data.summary_result.generated_output (string)

For full reference including supported models, see LLM Actions.

generate_structured_value_action

Generate structured JSON output matching a defined schema. Use for classification, entity extraction, and any task where you need typed output.

Action Name: mw.generate_structured_value_action

Input Parameters:

Example:

1
- action:
2
    action_name: mw.generate_structured_value_action
3
    output_key: classification_result
4
    input_args:
5
      payload: data.customer_review
6
      system_prompt: '''Analyze the sentiment of this review.'''
7
      output_schema: >-
8
        {
9
          "type": "object",
10
          "properties": {
11
            "sentiment": {"type": "string", "enum": ["positive", "negative", "neutral"]},
12
            "confidence": {"type": "number"}
13
          },
14
          "required": ["sentiment", "confidence"],
15
          "additionalProperties": false
16
        }

Response: data.classification_result.generated_output (object matching your schema)

For full reference including supported models, see LLM Actions.