Amazon Connect · Arazzo Workflow

Amazon Connect Start Task Contact and Stop It

Version 1.0.0

Create a task contact, confirm it through describe, then end the contact.

1 workflow 1 source API 1 provider
View Spec View on GitHub ChatContact CenterCustomer ServiceVoiceArtificial IntelligenceOmnichannelArazzoWorkflows

Provider

amazon-connect

Workflows

start-task-and-stop
Start a task contact, confirm it, and stop it.
Starts a task contact, reads it back through describeContact, then ends the contact with stopContact.
3 steps inputs: contactFlowId, description, instanceId, name outputs: channel, contactId
1
startTask
Start a new task contact against the specified contact flow.
2
confirmTask
Describe the task contact to confirm it was created before stopping it.
3
stopTask
End the task contact.

Source API Descriptions

Arazzo Workflow Specification

Raw ↑
arazzo: 1.0.1
info:
  title: Amazon Connect Start Task Contact and Stop It
  summary: Create a task contact, confirm it through describe, then end the contact.
  description: >-
    Drives the lifecycle of a task contact. The workflow starts a new task
    contact against a contact flow, describes it to confirm the task was created,
    and then stops the contact to close it out. This is useful for automated task
    creation paths that need to verify and immediately resolve a contact. Every
    step spells out its request inline so the flow can be read and executed
    without opening the underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: contactsApi
  url: ../openapi/amazon-connect-contacts-api-openapi.yml
  type: openapi
workflows:
- workflowId: start-task-and-stop
  summary: Start a task contact, confirm it, and stop it.
  description: >-
    Starts a task contact, reads it back through describeContact, then ends the
    contact with stopContact.
  inputs:
    type: object
    required:
    - instanceId
    - contactFlowId
    - name
    properties:
      instanceId:
        type: string
        description: The identifier of the Amazon Connect instance.
      contactFlowId:
        type: string
        description: The identifier of the contact flow to run for the task.
      name:
        type: string
        description: The name of the task.
      description:
        type: string
        description: A description of the task.
  steps:
  - stepId: startTask
    description: >-
      Start a new task contact against the specified contact flow.
    operationId: startTaskContact
    requestBody:
      contentType: application/json
      payload:
        InstanceId: $inputs.instanceId
        ContactFlowId: $inputs.contactFlowId
        Name: $inputs.name
        Description: $inputs.description
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      contactId: $response.body#/ContactId
  - stepId: confirmTask
    description: >-
      Describe the task contact to confirm it was created before stopping it.
    operationId: describeContact
    parameters:
    - name: InstanceId
      in: path
      value: $inputs.instanceId
    - name: ContactId
      in: path
      value: $steps.startTask.outputs.contactId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      channel: $response.body#/Contact/Channel
    onSuccess:
    - name: taskExists
      type: goto
      stepId: stopTask
      criteria:
      - context: $response.body
        condition: $.Contact.Id != null
        type: jsonpath
  - stepId: stopTask
    description: >-
      End the task contact.
    operationId: stopContact
    parameters:
    - name: InstanceId
      in: path
      value: $inputs.instanceId
    - name: ContactId
      in: path
      value: $steps.startTask.outputs.contactId
    requestBody:
      contentType: application/json
      payload:
        InstanceId: $inputs.instanceId
        ContactId: $steps.startTask.outputs.contactId
    successCriteria:
    - condition: $statusCode == 200
  outputs:
    contactId: $steps.startTask.outputs.contactId
    channel: $steps.confirmTask.outputs.channel

Work with this as data

Every workflow here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for arazzo workflows

4 MCP tools reach this
  • find_arazzoBrowse and filter every workflow in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This workflow
curl "https://apis.io/api/v1/arazzo/amazon-connect-start-task-and-stop-workflow"
All arazzo workflows
curl "https://apis.io/api/v1/arazzo?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.