Kata.ai · Arazzo Workflow

Build and deploy a Kata.ai bot

Version 1.0.0

Log in, create a project, push a bot revision, cut a deployment version, and bind an environment.

1 workflow 1 source API 1 provider
View Spec View on GitHub CompanyConversational AIChatbotsAI AgentsNatural Language UnderstandingNLUCustomer ExperienceMessagingIndonesiaBotsArazzoWorkflows

Provider

kataai

Workflows

buildAndDeployBot
End-to-end creation and deployment of a Kata Platform bot.
Authenticates against the Kata Platform Public API, creates a project, pushes a bot revision, creates a deployment version referencing that revision, and binds it to a named environment.
4 steps inputs: environmentName, environmentSlug, password, projectName, username, version outputs: environmentId, projectId
1
login
login
2
createProject
createProject
3
createDeploymentVersion
createDeploymentVersion
4
createEnvironment
createEnvironment

Source API Descriptions

Arazzo Workflow Specification

Raw ↑
arazzo: 1.0.1
info:
  title: Build and deploy a Kata.ai bot
  version: 1.0.0
  summary: Log in, create a project, push a bot revision, cut a deployment version, and bind an environment.
sourceDescriptions:
- name: platform
  url: ../openapi/kataai-platform-openapi.yml
  type: openapi
workflows:
- workflowId: buildAndDeployBot
  summary: End-to-end creation and deployment of a Kata Platform bot.
  description: >-
    Authenticates against the Kata Platform Public API, creates a project,
    pushes a bot revision, creates a deployment version referencing that
    revision, and binds it to a named environment.
  inputs:
    type: object
    required: [username, password, projectName]
    properties:
      username: { type: string }
      password: { type: string }
      projectName: { type: string, default: My New Project }
      version: { type: string, default: 0.0.1 }
      environmentName: { type: string, default: Development }
      environmentSlug: { type: string, default: my-bot-dev }
  steps:
  - stepId: login
    operationId: login
    requestBody:
      contentType: application/json
      payload:
        username: $inputs.username
        password: $inputs.password
    outputs:
      token: $response.body#/id
  - stepId: createProject
    operationId: createProject
    parameters:
    - name: Authorization
      in: header
      value: "Bearer $steps.login.outputs.token"
    requestBody:
      contentType: application/json
      payload:
        name: $inputs.projectName
        options:
          bot: true
          cms: true
          nlu: true
          timezone: 7
          nluVisibility: private
          nluLang: id
    outputs:
      projectId: $response.body#/id
      botRevision: $response.body#/botLatestRevision
  - stepId: createDeploymentVersion
    operationId: createDeploymentVersion
    parameters:
    - name: projectId
      in: path
      value: $steps.createProject.outputs.projectId
    - name: Authorization
      in: header
      value: "Bearer $steps.login.outputs.token"
    requestBody:
      contentType: application/json
      payload:
        version: $inputs.version
        botRevision: $steps.createProject.outputs.botRevision
    outputs:
      deploymentVersion: $response.body#/version
  - stepId: createEnvironment
    operationId: createEnvironment
    parameters:
    - name: projectId
      in: path
      value: $steps.createProject.outputs.projectId
    - name: Authorization
      in: header
      value: "Bearer $steps.login.outputs.token"
    requestBody:
      contentType: application/json
      payload:
        depId: $steps.createProject.outputs.projectId
        depVersion: $steps.createDeploymentVersion.outputs.deploymentVersion
        name: $inputs.environmentName
        slug: $inputs.environmentSlug
    outputs:
      environmentId: $response.body#/id
  outputs:
    projectId: $steps.createProject.outputs.projectId
    environmentId: $steps.createEnvironment.outputs.environmentId

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/kataai-build-and-deploy-bot"
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 email required.

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