> This page is for API Reference & Tools.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.moveworks.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.moveworks.com/_mcp/server.

# Create conversational process

POST https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes
Content-Type: application/json

Creates a conversational process and returns it with its server-assigned `id` and `version`.

Send the fields at the top level of the body. Don't send `id` or `version.num`; `version.change_description` is required. Anything this conversational process refers to must already exist.

Reference: https://docs.moveworks.com/api-reference/configuration-api/tool-studio/conversational-processes/create-conversational-process

## Authentication

- `Authorization` header (bearer token, required) — JWT bearer token authentication. Include the Configuration API key in the Authorization header as 'Bearer \<token>'.

## Request

### Body (application/json)

This endpoint expects a ConversationalProcessCreate.

- `signature` (FunctionSignatureSettingsCreate, required) — Name and description of the conversational process. The internal name is derived from the display name. Required.
- `conversation_flow` (ConversationBlockCreate, required) — The control flow of the process, built from sequential, switch, activity, return and no-op blocks. Required.
- `version` (VersionCreate, required) — Document version. On update, send back the num from your last read.
- `slots` (list of ConversationalProcessSlotCreate, optional) — Input values (slots) the process collects from the user and uses as variables in the conversation flow.

## Response

### 200

The created conversational process

- `id` (string, optional) — Unique identifier of the conversational process, assigned by the server. Cannot be changed.
- `signature` (FunctionSignatureSettings, optional) — Name and description of the conversational process. The internal name is derived from the display name. Required.
- `slots` (list of ConversationalProcessSlot, optional) — Input values (slots) the process collects from the user and uses as variables in the conversation flow.
- `conversation_flow` (ConversationBlock, optional) — The control flow of the process, built from sequential, switch, activity, return and no-op blocks. Required.
- `updated_time` (datetime, optional) — When the configuration was last updated.
- `updated_by` (string, optional) — Who last updated the configuration.
- `version` (Version, optional) — Document version. On update, send back the num from your last read.

## Errors

### 400 Bad Request Error

Bad request

- `error` (ErrorResponseError, required)

### 401 Unauthorized Error

Unauthorized - the `Authorization` header is missing or the token is invalid

- `error` (ErrorResponseError, required)

### 403 Forbidden Error

Forbidden - the API key isn't allowed to change this configuration, or the configuration is frozen for your organization

- `error` (ErrorResponseError, required)

### 409 Conflict Error

Conflict - `version.num` doesn't match the stored version (someone changed it since your last read; read it again and retry), or the item already exists

- `error` (ErrorResponseError, required)

### 429 Too Many Requests Error

Too many requests - the organization exceeded the Configuration API rate limit. Back off and retry.

- `error` (ErrorResponseError, required)

### 500 Internal Server Error

Internal server error - retry the request

- `error` (ErrorResponseError, required)

## Types

### FunctionSignatureSettingsCreate

- `name` (string, required) — Technical name used to reference this function. Must start with a letter and contain only letters, digits and underscores; 2 to 64 characters.
- `description` (string, required) — Description of what this function does. 12 to 1024 characters.
- `arguments` (list of ArgumentSettingsCreate, optional) — Input arguments the function accepts.
- `result_schema` (FunctionSignatureSettingsCreateResultSchema, optional) — JSON schema describing the function's output.
- `display_name` (string, optional) — Human-readable name of the function. 2 to 64 characters. If empty, name is shown instead.

### ConversationBlockCreate

- `sequential` (ConversationSequentialCreate, optional) — A sequence of blocks run in order.
- `switch` (ConversationSwitchCreate, optional) — A set of conditional cases plus a default; exactly one branch runs.
- `activity` (ConversationActivityCreate, optional) — A single activity, such as running an action or showing text, knowledge or a form.
- `return` (ConversationReturn, optional) — Exits the entire conversation flow.
- `noop` (ConversationNoop, optional) — A block that does nothing, used as a pass-through in the flow.

### VersionCreate

- `change_description` (string, required) — A short note describing this change. Required on every create and update.

### ConversationalProcessSlotCreate

- `name` (string, required) — Unique slot name used to refer to the slot in the conversation flow. Must start with a letter and contain only letters, digits and underscores (2 to 64 characters).
- `description` (string, required) — Natural language description of the slot that tells the assistant what to ask the user. Required.
- `type` (TypeSettingsCreate, required) — Data type of the slot value, such as string, List[User] or a custom data type. Required.
- `resolution` (ConversationalProcessSlotResolutionCreate, optional) — How the slot value is resolved, inferred or requested from the user.
- `validations` (list of ConversationalProcessSlotValidationCreate, optional) — Rules checked against the resolved slot value. The resolved value is available as value.

### FunctionSignatureSettings

- `name` (string, optional) — Technical name used to reference this function. Must start with a letter and contain only letters, digits and underscores; 2 to 64 characters.
- `description` (string, optional) — Description of what this function does. 12 to 1024 characters.
- `arguments` (list of ArgumentSettings, optional) — Input arguments the function accepts.
- `result_schema` (FunctionSignatureSettingsResultSchema, optional) — JSON schema describing the function's output.
- `display_name` (string, optional) — Human-readable name of the function. 2 to 64 characters. If empty, name is shown instead.

### ConversationalProcessSlot

- `name` (string, optional) — Unique slot name used to refer to the slot in the conversation flow. Must start with a letter and contain only letters, digits and underscores (2 to 64 characters).
- `description` (string, optional) — Natural language description of the slot that tells the assistant what to ask the user. Required.
- `type` (TypeSettings, optional) — Data type of the slot value, such as string, List[User] or a custom data type. Required.
- `resolution` (ConversationalProcessSlotResolution, optional) — How the slot value is resolved, inferred or requested from the user.
- `validations` (list of ConversationalProcessSlotValidation, optional) — Rules checked against the resolved slot value. The resolved value is available as value.

### ConversationBlock

- `sequential` (ConversationSequential, optional) — A sequence of blocks run in order.
- `switch` (ConversationSwitch, optional) — A set of conditional cases plus a default; exactly one branch runs.
- `activity` (ConversationActivity, optional) — A single activity, such as running an action or showing text, knowledge or a form.
- `return` (ConversationReturn, optional) — Exits the entire conversation flow.
- `noop` (ConversationNoop, optional) — A block that does nothing, used as a pass-through in the flow.

### Version

- `num` (integer, optional) — Version number set by the server. On update, send the num from your last read; a stale num is rejected as a conflict.
- `change_description` (string, optional) — A short note describing this change. Required on every create and update.

### ErrorResponseError

- `code` (string, optional) — A machine-readable error code.
- `message` (string, optional) — What went wrong, and for a rejected field, which rule it broke.

### ArgumentSettingsCreate

- `name` (string, required) — Name of the argument. Must start with a letter and contain only letters, digits and underscores; 2 to 64 characters.
- `description` (string, required) — Description of the argument. 2 to 256 characters.
- `type` (TypeSettingsCreate, required) — Data type of the argument, e.g. string, List[User] or a custom type. Required.
- `required` (boolean, optional) — If true, a value must be provided for this argument.
- `default_value` (ArgumentSettingsCreateDefaultValue, optional, nullable) — Value used for this argument when none is provided.
- `example_value` (ArgumentSettingsCreateExampleValue, optional, nullable) — Example value for this argument.

### FunctionSignatureSettingsCreateResultSchema

JSON schema describing the function's output.

### ConversationSequentialCreate

- `steps` (list of ConversationBlockCreate, optional) — Blocks run in order.

### ConversationSwitchCreate

- `prerequisite_slots` (list of string, optional) — Names of slots that must be resolved before the cases are evaluated.
- `cases` (list of ConversationSwitchCaseCreate, optional) — Conditional cases evaluated in order; the first matching case runs.
- `default` (ConversationBlockCreate, optional) — Block that runs when no case matches.

### ConversationActivityCreate

- `prerequisite_slots` (list of string, optional) — Names of slots that must be resolved before the activity runs.
- `output_slot` (string, optional) — Name under which the activity result is stored for use later in the flow.
- `action` (ActionInvocationCreate, optional) — Runs an action with the given input and output mappings.
- `text` (ConversationText, optional) — Shows a text message to the user.
- `knowledge` (ConversationKnowledge, optional) — Shows a knowledge article to the user.
- `form` (ConversationForm, optional) — Shows a form to the user.
- `needs_confirmation` (boolean, optional) — If true, the user must confirm before the activity runs.
- `wait_for_completion` (boolean, optional) — If true, the flow waits for the action to finish before continuing. New actions default to true.

### ConversationReturn

### ConversationNoop

### TypeSettingsCreate

- `primitive` (enum, optional) — A primitive type. One of: string, integer, number, boolean, array, object.
  - Allowed values: `string`, `integer`, `number`, `boolean`, `array`, `object`
- `native` (enum, optional) — A Moveworks-defined type. One of: User, File, ariba.v1.CatalogItem, workday.v1.JobProfile, Room, Group.
  - Allowed values: `User`, `File`, `ariba.v1.CatalogItem`, `workday.v1.JobProfile`, `Room`, `Group`
- `custom` (string, optional) — Name of a custom type registered in your organization. ID of an existing data_type (GET /configurations/v1alpha1/platform/extensions/data-types).
- `list` (boolean, optional) — If true, the argument is a list of the selected type rather than a single value.

### ConversationalProcessSlotResolutionCreate

- `strategy_invocation` (ResolutionStrategyInvocationCreate, optional) — Resolution strategy used to resolve the slot value. If omitted, the default resolution strategy for the data type is used.
- `must_request` (boolean, optional) — If true, the assistant always explicitly asks the user for this slot value.
- `value_population_policy` (ConversationalProcessSlotValuePopulationPolicyCreate, optional) — Controls whether the value is inferred or requested, and an optional fallback value.

### ConversationalProcessSlotValidationCreate

- `condition` (string, optional) — DSL rule evaluated against the slot value. The value is valid if the result is truthy. Must be a valid MWDSL expression.
- `error_message` (string, optional) — Message shown to the user when the validation fails. Supports Mustache templates.

### ArgumentSettings

- `name` (string, optional) — Name of the argument. Must start with a letter and contain only letters, digits and underscores; 2 to 64 characters.
- `description` (string, optional) — Description of the argument. 2 to 256 characters.
- `type` (TypeSettings, optional) — Data type of the argument, e.g. string, List[User] or a custom type. Required.
- `required` (boolean, optional) — If true, a value must be provided for this argument.
- `default_value` (ArgumentSettingsDefaultValue, optional, nullable) — Value used for this argument when none is provided.
- `example_value` (ArgumentSettingsExampleValue, optional, nullable) — Example value for this argument.

### FunctionSignatureSettingsResultSchema

JSON schema describing the function's output.

### TypeSettings

- `primitive` (enum, optional) — A primitive type. One of: string, integer, number, boolean, array, object.
  - Allowed values: `string`, `integer`, `number`, `boolean`, `array`, `object`
- `native` (enum, optional) — A Moveworks-defined type. One of: User, File, ariba.v1.CatalogItem, workday.v1.JobProfile, Room, Group.
  - Allowed values: `User`, `File`, `ariba.v1.CatalogItem`, `workday.v1.JobProfile`, `Room`, `Group`
- `custom` (string, optional) — Name of a custom type registered in your organization. ID of an existing data_type (GET /configurations/v1alpha1/platform/extensions/data-types).
- `list` (boolean, optional) — If true, the argument is a list of the selected type rather than a single value.

### ConversationalProcessSlotResolution

- `strategy_invocation` (ResolutionStrategyInvocation, optional) — Resolution strategy used to resolve the slot value. If omitted, the default resolution strategy for the data type is used.
- `must_request` (boolean, optional) — If true, the assistant always explicitly asks the user for this slot value.
- `value_population_policy` (ConversationalProcessSlotValuePopulationPolicy, optional) — Controls whether the value is inferred or requested, and an optional fallback value.

### ConversationalProcessSlotValidation

- `condition` (string, optional) — DSL rule evaluated against the slot value. The value is valid if the result is truthy.
- `error_message` (string, optional) — Message shown to the user when the validation fails. Supports Mustache templates.

### ConversationSequential

- `steps` (list of ConversationBlock, optional) — Blocks run in order.

### ConversationSwitch

- `prerequisite_slots` (list of string, optional) — Names of slots that must be resolved before the cases are evaluated.
- `cases` (list of ConversationSwitchCase, optional) — Conditional cases evaluated in order; the first matching case runs.
- `default` (ConversationBlock, optional) — Block that runs when no case matches.

### ConversationActivity

- `prerequisite_slots` (list of string, optional) — Names of slots that must be resolved before the activity runs.
- `output_slot` (string, optional) — Name under which the activity result is stored for use later in the flow.
- `action` (ActionInvocation, optional) — Runs an action with the given input and output mappings.
- `text` (ConversationText, optional) — Shows a text message to the user.
- `knowledge` (ConversationKnowledge, optional) — Shows a knowledge article to the user.
- `form` (ConversationForm, optional) — Shows a form to the user.
- `needs_confirmation` (boolean, optional) — If true, the user must confirm before the activity runs.
- `wait_for_completion` (boolean, optional) — If true, the flow waits for the action to finish before continuing. New actions default to true.

### ArgumentSettingsCreateDefaultValue

Value used for this argument when none is provided.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### ArgumentSettingsCreateExampleValue

Example value for this argument.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### ConversationSwitchCaseCreate

- `then` (ConversationBlockCreate, required) — Block that runs when the condition matches. Required.
- `condition` (string, optional) — DSL condition that selects this case when it evaluates to true. Must be a valid MWDSL expression.

### ActionInvocationCreate

- `action_id` (ActionIdCreate, required) — The action to call.
- `input_mapper` (ActionInvocationCreateInputMapper, optional, nullable) — Data mapping that builds the action's input arguments.
- `output_mapper` (ActionInvocationCreateOutputMapper, optional, nullable) — Data mapping applied to the action's result.

### ConversationText

- `template` (string, optional) — Text shown to the user. Supports Mustache templates.

### ConversationKnowledge

- `document_id` (ConversationKnowledgeDocumentId, optional) — ID of the knowledge article to show.
- `document_title` (string, optional) — Title of the knowledge article, used for preview.

### ConversationForm

- `form_id` (string, optional) — ID of the form to show.
- `form_title` (string, optional) — Title of the form, used for preview.

### ResolutionStrategyInvocationCreate

- `strategy` (ResolutionStrategySelectionCreate, optional) — Resolution strategy used to find the value, either a custom strategy or a built-in one.
- `input_mappers` (list of ResolverMethodInputMapper, optional) — Mappings from the invocation context to the inputs of each resolver method in the strategy.

### ConversationalProcessSlotValuePopulationPolicyCreate

- `inference_type` (enum, optional) — Whether the assistant always requests the value from the user or always infers it. If omitted, the assistant uses its best judgement at runtime.
  - Allowed values: `CONVERSATIONAL_PROCESS_INFERENCE_TYPE_UNSPECIFIED`, `CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_REQUEST`, `CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER`
- `fallback_expression` (string, optional) — Optional DSL expression that calculates a default value for the slot. Must be a valid MWDSL expression.

### ArgumentSettingsDefaultValue

Value used for this argument when none is provided.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### ArgumentSettingsExampleValue

Example value for this argument.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### ResolutionStrategyInvocation

- `strategy` (ResolutionStrategySelection, optional) — Resolution strategy used to find the value, either a custom strategy or a built-in one.
- `input_mappers` (list of ResolverMethodInputMapper, optional) — Mappings from the invocation context to the inputs of each resolver method in the strategy.

### ConversationalProcessSlotValuePopulationPolicy

- `inference_type` (enum, optional) — Whether the assistant always requests the value from the user or always infers it. If omitted, the assistant uses its best judgement at runtime.
  - Allowed values: `CONVERSATIONAL_PROCESS_INFERENCE_TYPE_UNSPECIFIED`, `CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_REQUEST`, `CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER`
- `fallback_expression` (string, optional) — Optional DSL expression that calculates a default value for the slot.

### ConversationSwitchCase

- `condition` (string, optional) — DSL condition that selects this case when it evaluates to true.
- `then` (ConversationBlock, optional) — Block that runs when the condition matches. Required.

### ActionInvocation

- `action_id` (ActionId, optional) — The action to call.
- `input_mapper` (ActionInvocationInputMapper, optional, nullable) — Data mapping that builds the action's input arguments.
- `output_mapper` (ActionInvocationOutputMapper, optional, nullable) — Data mapping applied to the action's result.

### ActionIdCreate

- `http_action` (string, optional) — Name of an HTTP action to call. Set exactly one action type.
- `compound_action` (string, optional) — Name of a compound action to call. Set exactly one action type.
- `script_action` (string, optional) — Name of a script action to call. Set exactly one action type.
- `built_in_action` (enum, optional) — Name of a built-in Moveworks action to call, such as get_user_by_email or send_plaintext_chat_notification. Set exactly one action type.
  - Allowed values: `batch_get_users_by_email`, `batch_send_plaintext_chat_notification`, `create_generic_approval_request`, `generate_structured_value_action`, `generate_text_action`, `get_user_by_email`, `llm_decision_action`, `run_script_action`, `send_plaintext_chat_notification`, `summarize_text_action`

### ActionInvocationCreateInputMapper

Data mapping that builds the action's input arguments.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### ActionInvocationCreateOutputMapper

Data mapping applied to the action's result.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### ConversationKnowledgeDocumentId

ID of the knowledge article to show.

- integer
- string

### ResolutionStrategySelectionCreate

- `custom_strategy` (CustomResolutionStrategyCreate, optional) — A custom resolution strategy defined inline with its resolver methods.
- `native_strategy` (enum, optional) — A built-in resolution strategy. Allowed value: user_resolution_strategy.
  - Allowed values: `user_resolution_strategy`

### ResolverMethodInputMapper

- `resolver_method_id` (string, optional) — ID of the resolver method this mapping applies to. Must match a method ID in the selected strategy.
- `input_mapper` (ResolverMethodInputMapperInputMapper, optional, nullable) — Data mapper from the invocation context, available under 'args', to the resolver method's input schema.

### ResolutionStrategySelection

- `custom_strategy` (CustomResolutionStrategy, optional) — A custom resolution strategy defined inline with its resolver methods.
- `native_strategy` (enum, optional) — A built-in resolution strategy. Allowed value: user_resolution_strategy.
  - Allowed values: `user_resolution_strategy`

### ActionId

- `http_action` (string, optional) — Name of an HTTP action to call. Set exactly one action type.
- `compound_action` (string, optional) — Name of a compound action to call. Set exactly one action type.
- `script_action` (string, optional) — Name of a script action to call. Set exactly one action type.
- `built_in_action` (enum, optional) — Name of a built-in Moveworks action to call, such as get_user_by_email or send_plaintext_chat_notification. Set exactly one action type.
  - Allowed values: `batch_get_users_by_email`, `batch_send_plaintext_chat_notification`, `create_generic_approval_request`, `generate_structured_value_action`, `generate_text_action`, `get_user_by_email`, `llm_decision_action`, `run_script_action`, `send_plaintext_chat_notification`, `summarize_text_action`

### ActionInvocationInputMapper

Data mapping that builds the action's input arguments.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### ActionInvocationOutputMapper

Data mapping applied to the action's result.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### CustomResolutionStrategyCreate

- `resolver_methods` (list of ResolverMethodCreate, optional) — Independent methods that can each resolve a value.

### ResolverMethodInputMapperInputMapper

Data mapper from the invocation context, available under 'args', to the resolver method's input schema.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### CustomResolutionStrategy

- `resolver_methods` (list of ResolverMethod, optional) — Independent methods that can each resolve a value.

### ResolverMethodCreate

- `id` (string, required) — Unique name of the resolver method. Letters, digits and underscores only, starting with a letter or underscore; up to 64 characters.
- `input_schema` (ResolverMethodCreateInputSchema, optional) — JSON schema describing the inputs this method accepts.
- `dynamic` (DynamicResolverCreate, optional) — Looks up candidate values by running an action.
- `static` (StaticResolverCreate, optional) — Chooses a value from a fixed list of options.

### ResolverMethod

- `id` (string, optional) — Unique name of the resolver method. Letters, digits and underscores only, starting with a letter or underscore; up to 64 characters.
- `input_schema` (ResolverMethodInputSchema, optional) — JSON schema describing the inputs this method accepts.
- `dynamic` (DynamicResolver, optional) — Looks up candidate values by running an action.
- `static` (StaticResolver, optional) — Chooses a value from a fixed list of options.

### ResolverMethodCreateInputSchema

JSON schema describing the inputs this method accepts.

### DynamicResolverCreate

- `action_id` (ActionIdCreate, required) — Action this resolver method runs. The action must return synchronously.
- `input_mapper` (DynamicResolverCreateInputMapper, optional, nullable) — Data mapper from the method's inputs to the action's arguments. Input values are available under 'data'.
- `output_mapper` (DynamicResolverCreateOutputMapper, optional, nullable) — Data mapper from the action result, available under 'response', to the resolved value or list of candidate values.
- `produces_multiple_candidates` (boolean, optional) — If true, the method returns a list of candidate values that the user must choose from.

### StaticResolverCreate

- `options` (list of StaticOptionCreate, required) — Fixed candidate values to choose from. At least one is required.

### ResolverMethodInputSchema

JSON schema describing the inputs this method accepts.

### DynamicResolver

- `action_id` (ActionId, optional) — Action this resolver method runs. The action must return synchronously.
- `input_mapper` (DynamicResolverInputMapper, optional, nullable) — Data mapper from the method's inputs to the action's arguments. Input values are available under 'data'.
- `output_mapper` (DynamicResolverOutputMapper, optional, nullable) — Data mapper from the action result, available under 'response', to the resolved value or list of candidate values.
- `produces_multiple_candidates` (boolean, optional) — If true, the method returns a list of candidate values that the user must choose from.

### StaticResolver

- `options` (list of StaticOption, optional) — Fixed candidate values to choose from. At least one is required.

### DynamicResolverCreateInputMapper

Data mapper from the method's inputs to the action's arguments. Input values are available under 'data'.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### DynamicResolverCreateOutputMapper

Data mapper from the action result, available under 'response', to the resolved value or list of candidate values.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### StaticOptionCreate

- `value` (StaticOptionCreateValue, required, nullable) — The full candidate value.
- `display_name` (string, optional) — Short, user-friendly name for this candidate value.

### DynamicResolverInputMapper

Data mapper from the method's inputs to the action's arguments. Input values are available under 'data'.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### DynamicResolverOutputMapper

Data mapper from the action result, available under 'response', to the resolved value or list of candidate values.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### StaticOption

- `display_name` (string, optional) — Short, user-friendly name for this candidate value.
- `value` (StaticOptionValue, optional, nullable) — The full candidate value.

### StaticOptionCreateValue

The full candidate value.

- string
- double
- integer
- boolean
- map from string to any
- list of any

### StaticOptionValue

The full candidate value.

- string
- double
- integer
- boolean
- map from string to any
- list of any

## Examples

### Conversational Processes endpoints_createConversationalProcess_example

**Response**

```json
{
  "id": "3f6c1e2a-8b4d-4c7e-9a1f-2d5b6c7e8f90",
  "signature": {
    "description": "Looks up a purchase order by number and reports its status.",
    "display_name": "Purchase Order Lookup"
  },
  "slots": [
    {
      "name": "po_number",
      "description": "The purchase order number the user is asking about.",
      "type": {
        "primitive": "string"
      },
      "resolution": {
        "must_request": true,
        "value_population_policy": {
          "inference_type": "CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER"
        }
      }
    }
  ],
  "conversation_flow": {
    "sequential": {
      "steps": [
        {
          "activity": {
            "prerequisite_slots": [
              "po_number"
            ],
            "output_slot": "purchase_order",
            "action": {
              "action_id": {
                "http_action": "1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411"
              },
              "input_mapper": {
                "po_number": "data.po_number"
              }
            },
            "needs_confirmation": false
          }
        },
        {
          "return": {}
        }
      ]
    }
  },
  "updated_time": "2026-11-12T18:04:11Z",
  "updated_by": "admin@example.com",
  "version": {
    "num": 1,
    "change_description": "Initial version."
  }
}
```

**SDK Code**

```python Conversational Processes endpoints_createConversationalProcess_example
import requests

url = "https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes"

headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, headers=headers)

print(response.json())
```

```javascript Conversational Processes endpoints_createConversationalProcess_example
const url = 'https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes';
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go Conversational Processes endpoints_createConversationalProcess_example
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes"

	req, _ := http.NewRequest("POST", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby Conversational Processes endpoints_createConversationalProcess_example
require 'uri'
require 'net/http'

url = URI("https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body
```

```java Conversational Processes endpoints_createConversationalProcess_example
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes")
  .header("Authorization", "Bearer <token>")
  .asString();
```

```php Conversational Processes endpoints_createConversationalProcess_example
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes', [
  'headers' => [
    'Authorization' => 'Bearer <token>',
  ],
]);

echo $response->getBody();
```

```csharp Conversational Processes endpoints_createConversationalProcess_example
using RestSharp;

var client = new RestClient("https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
IRestResponse response = client.Execute(request);
```

```swift Conversational Processes endpoints_createConversationalProcess_example
import Foundation

let headers = ["Authorization": "Bearer <token>"]

let request = NSMutableURLRequest(url: NSURL(string: "https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### Create a conversational process

**Request**

```json
{
  "signature": {
    "name": "example",
    "description": "Looks up a purchase order by number and reports its status.",
    "display_name": "Purchase Order Lookup"
  },
  "conversation_flow": {
    "sequential": {
      "steps": [
        {
          "activity": {
            "prerequisite_slots": [
              "po_number"
            ],
            "output_slot": "purchase_order",
            "action": {
              "action_id": {
                "http_action": "1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411"
              },
              "input_mapper": {
                "po_number": "data.po_number"
              }
            },
            "needs_confirmation": false
          }
        },
        {
          "return": {}
        }
      ]
    }
  },
  "version": {
    "change_description": "Initial version."
  },
  "slots": [
    {
      "name": "po_number",
      "description": "The purchase order number the user is asking about.",
      "type": {
        "primitive": "string"
      },
      "resolution": {
        "must_request": true,
        "value_population_policy": {
          "inference_type": "CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER"
        }
      }
    }
  ]
}
```

**Response**

```json
{
  "id": "3f6c1e2a-8b4d-4c7e-9a1f-2d5b6c7e8f90",
  "signature": {
    "description": "Looks up a purchase order by number and reports its status.",
    "display_name": "Purchase Order Lookup"
  },
  "slots": [
    {
      "name": "po_number",
      "description": "The purchase order number the user is asking about.",
      "type": {
        "primitive": "string"
      },
      "resolution": {
        "must_request": true,
        "value_population_policy": {
          "inference_type": "CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER"
        }
      }
    }
  ],
  "conversation_flow": {
    "sequential": {
      "steps": [
        {
          "activity": {
            "prerequisite_slots": [
              "po_number"
            ],
            "output_slot": "purchase_order",
            "action": {
              "action_id": {
                "http_action": "1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411"
              },
              "input_mapper": {
                "po_number": "data.po_number"
              }
            },
            "needs_confirmation": false
          }
        },
        {
          "return": {}
        }
      ]
    }
  },
  "updated_time": "2026-11-12T18:04:11Z",
  "updated_by": "admin@example.com",
  "version": {
    "num": 1,
    "change_description": "Initial version."
  }
}
```

**SDK Code**

```python Create a conversational process
import requests

url = "https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes"

payload = {
    "signature": {
        "name": "example",
        "description": "Looks up a purchase order by number and reports its status.",
        "display_name": "Purchase Order Lookup"
    },
    "conversation_flow": { "sequential": { "steps": [{ "activity": {
                        "prerequisite_slots": ["po_number"],
                        "output_slot": "purchase_order",
                        "action": {
                            "action_id": { "http_action": "1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411" },
                            "input_mapper": { "po_number": "data.po_number" }
                        },
                        "needs_confirmation": False
                    } }, { "return": {} }] } },
    "version": { "change_description": "Initial version." },
    "slots": [
        {
            "name": "po_number",
            "description": "The purchase order number the user is asking about.",
            "type": { "primitive": "string" },
            "resolution": {
                "must_request": True,
                "value_population_policy": { "inference_type": "CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER" }
            }
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript Create a conversational process
const url = 'https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"signature":{"name":"example","description":"Looks up a purchase order by number and reports its status.","display_name":"Purchase Order Lookup"},"conversation_flow":{"sequential":{"steps":[{"activity":{"prerequisite_slots":["po_number"],"output_slot":"purchase_order","action":{"action_id":{"http_action":"1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411"},"input_mapper":{"po_number":"data.po_number"}},"needs_confirmation":false}},{"return":{}}]}},"version":{"change_description":"Initial version."},"slots":[{"name":"po_number","description":"The purchase order number the user is asking about.","type":{"primitive":"string"},"resolution":{"must_request":true,"value_population_policy":{"inference_type":"CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER"}}}]}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go Create a conversational process
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes"

	payload := strings.NewReader("{\n  \"signature\": {\n    \"name\": \"example\",\n    \"description\": \"Looks up a purchase order by number and reports its status.\",\n    \"display_name\": \"Purchase Order Lookup\"\n  },\n  \"conversation_flow\": {\n    \"sequential\": {\n      \"steps\": [\n        {\n          \"activity\": {\n            \"prerequisite_slots\": [\n              \"po_number\"\n            ],\n            \"output_slot\": \"purchase_order\",\n            \"action\": {\n              \"action_id\": {\n                \"http_action\": \"1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411\"\n              },\n              \"input_mapper\": {\n                \"po_number\": \"data.po_number\"\n              }\n            },\n            \"needs_confirmation\": false\n          }\n        },\n        {\n          \"return\": {}\n        }\n      ]\n    }\n  },\n  \"version\": {\n    \"change_description\": \"Initial version.\"\n  },\n  \"slots\": [\n    {\n      \"name\": \"po_number\",\n      \"description\": \"The purchase order number the user is asking about.\",\n      \"type\": {\n        \"primitive\": \"string\"\n      },\n      \"resolution\": {\n        \"must_request\": true,\n        \"value_population_policy\": {\n          \"inference_type\": \"CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER\"\n        }\n      }\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby Create a conversational process
require 'uri'
require 'net/http'

url = URI("https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"signature\": {\n    \"name\": \"example\",\n    \"description\": \"Looks up a purchase order by number and reports its status.\",\n    \"display_name\": \"Purchase Order Lookup\"\n  },\n  \"conversation_flow\": {\n    \"sequential\": {\n      \"steps\": [\n        {\n          \"activity\": {\n            \"prerequisite_slots\": [\n              \"po_number\"\n            ],\n            \"output_slot\": \"purchase_order\",\n            \"action\": {\n              \"action_id\": {\n                \"http_action\": \"1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411\"\n              },\n              \"input_mapper\": {\n                \"po_number\": \"data.po_number\"\n              }\n            },\n            \"needs_confirmation\": false\n          }\n        },\n        {\n          \"return\": {}\n        }\n      ]\n    }\n  },\n  \"version\": {\n    \"change_description\": \"Initial version.\"\n  },\n  \"slots\": [\n    {\n      \"name\": \"po_number\",\n      \"description\": \"The purchase order number the user is asking about.\",\n      \"type\": {\n        \"primitive\": \"string\"\n      },\n      \"resolution\": {\n        \"must_request\": true,\n        \"value_population_policy\": {\n          \"inference_type\": \"CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER\"\n        }\n      }\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body
```

```java Create a conversational process
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"signature\": {\n    \"name\": \"example\",\n    \"description\": \"Looks up a purchase order by number and reports its status.\",\n    \"display_name\": \"Purchase Order Lookup\"\n  },\n  \"conversation_flow\": {\n    \"sequential\": {\n      \"steps\": [\n        {\n          \"activity\": {\n            \"prerequisite_slots\": [\n              \"po_number\"\n            ],\n            \"output_slot\": \"purchase_order\",\n            \"action\": {\n              \"action_id\": {\n                \"http_action\": \"1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411\"\n              },\n              \"input_mapper\": {\n                \"po_number\": \"data.po_number\"\n              }\n            },\n            \"needs_confirmation\": false\n          }\n        },\n        {\n          \"return\": {}\n        }\n      ]\n    }\n  },\n  \"version\": {\n    \"change_description\": \"Initial version.\"\n  },\n  \"slots\": [\n    {\n      \"name\": \"po_number\",\n      \"description\": \"The purchase order number the user is asking about.\",\n      \"type\": {\n        \"primitive\": \"string\"\n      },\n      \"resolution\": {\n        \"must_request\": true,\n        \"value_population_policy\": {\n          \"inference_type\": \"CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER\"\n        }\n      }\n    }\n  ]\n}")
  .asString();
```

```php Create a conversational process
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes', [
  'body' => '{
  "signature": {
    "name": "example",
    "description": "Looks up a purchase order by number and reports its status.",
    "display_name": "Purchase Order Lookup"
  },
  "conversation_flow": {
    "sequential": {
      "steps": [
        {
          "activity": {
            "prerequisite_slots": [
              "po_number"
            ],
            "output_slot": "purchase_order",
            "action": {
              "action_id": {
                "http_action": "1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411"
              },
              "input_mapper": {
                "po_number": "data.po_number"
              }
            },
            "needs_confirmation": false
          }
        },
        {
          "return": {}
        }
      ]
    }
  },
  "version": {
    "change_description": "Initial version."
  },
  "slots": [
    {
      "name": "po_number",
      "description": "The purchase order number the user is asking about.",
      "type": {
        "primitive": "string"
      },
      "resolution": {
        "must_request": true,
        "value_population_policy": {
          "inference_type": "CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER"
        }
      }
    }
  ]
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp Create a conversational process
using RestSharp;

var client = new RestClient("https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"signature\": {\n    \"name\": \"example\",\n    \"description\": \"Looks up a purchase order by number and reports its status.\",\n    \"display_name\": \"Purchase Order Lookup\"\n  },\n  \"conversation_flow\": {\n    \"sequential\": {\n      \"steps\": [\n        {\n          \"activity\": {\n            \"prerequisite_slots\": [\n              \"po_number\"\n            ],\n            \"output_slot\": \"purchase_order\",\n            \"action\": {\n              \"action_id\": {\n                \"http_action\": \"1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411\"\n              },\n              \"input_mapper\": {\n                \"po_number\": \"data.po_number\"\n              }\n            },\n            \"needs_confirmation\": false\n          }\n        },\n        {\n          \"return\": {}\n        }\n      ]\n    }\n  },\n  \"version\": {\n    \"change_description\": \"Initial version.\"\n  },\n  \"slots\": [\n    {\n      \"name\": \"po_number\",\n      \"description\": \"The purchase order number the user is asking about.\",\n      \"type\": {\n        \"primitive\": \"string\"\n      },\n      \"resolution\": {\n        \"must_request\": true,\n        \"value_population_policy\": {\n          \"inference_type\": \"CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER\"\n        }\n      }\n    }\n  ]\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift Create a conversational process
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "signature": [
    "name": "example",
    "description": "Looks up a purchase order by number and reports its status.",
    "display_name": "Purchase Order Lookup"
  ],
  "conversation_flow": ["sequential": ["steps": [["activity": [
            "prerequisite_slots": ["po_number"],
            "output_slot": "purchase_order",
            "action": [
              "action_id": ["http_action": "1b7d4f5a-2c88-4e0b-9f31-7c5a0d9e4411"],
              "input_mapper": ["po_number": "data.po_number"]
            ],
            "needs_confirmation": false
          ]], ["return": []]]]],
  "version": ["change_description": "Initial version."],
  "slots": [
    [
      "name": "po_number",
      "description": "The purchase order number the user is asking about.",
      "type": ["primitive": "string"],
      "resolution": [
        "must_request": true,
        "value_population_policy": ["inference_type": "CONVERSATIONAL_PROCESS_INFERENCE_TYPE_ALWAYS_INFER"]
      ]
    ]
  ]
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.moveworks.ai/configurations/v1alpha1/platform/extensions/conversational-processes")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```