> ## Documentation Index
> Fetch the complete documentation index at: https://www.voiceflow.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Workato integration

> Connect Voiceflow to Workato to submit a confirmed callback request to an API recipe and return the reference created by your support workflow.

## Overview

Voiceflow integrates with Workato so your AI agent can submit a confirmed callback request to an API recipe and return the reference created by your support workflow. Workato runs the external workflow; Voiceflow calls its approved endpoint and uses the response in the conversation.

### Examples of when to use Workato

- **[Connect the business service](#connecting-workato)** — prepare its authorization, schema and test resources.
- **[Record a callback request](#run-request)** — invoke the configured service and interpret its current result.
- **[Recover a failed request](#maintaining-the-connection)** — inspect execution and downstream state before retrying.

#### Studio

Use an editable test project in [Agent studio](https://creator.voiceflow.com). Your integration developer or administrator prepares the service below, supplies its endpoint and credentials, and gives you a verified test request plus its expected result. Keep provider-side deployment with that owner.

#### Developer

Use a [Voiceflow personal or service key](/docs/api-reference/authentication) with project access, a current [Voiceflow CLI](/docs/cli/install) and the selected test [Environment](/docs/documentation/deploy/environments/overview). You prepare the provider service and create, execute and attach the Voiceflow request separately. The examples use a test project; they can read or change connected systems.

<a id="connecting-workato"></a>

## Connecting Workato

Prepare a deployed endpoint and the credentials for its approved operation.

### Prepare the provider service

#### Studio

Ask your Workato administrator or integration developer to complete the service setup linked below. Obtain all four handoff items before creating the Voiceflow tool:

- The deployed HTTPS endpoint and its exact authentication headers.
- The credential value for the Voiceflow Secret.
- A request schema, response schema and verified test customer/resource.
- A successful test response and a rejected unauthorized request, confirmed in the provider's execution history.

The sample request fields on this page are a recipe contract for your existing workflow. Have the owner map them to that workflow; a provider account alone does not create this endpoint.

#### Developer

### 1. Create the API recipe

Your Workato administrator needs **API Platform** access and privileges to create recipes, collections and endpoints. In an existing project folder, create an **API recipe** with **API platform by Workato → New API request**. Set request content to JSON and define `request_id`, `customer_id`, `reason` and `callback_number` as strings. Use the customer ID your application has verified; the recipe must check which customer the caller may act for.

### 2. Return the saved request

Connect the recipe to your existing callback queue. Validate the confirmed number and reason, and deduplicate `request_id` before creating work. Configure the trigger's JSON response schema with `request_id` and `status`. Finish the successful path with **Respond to API request**, mapping the saved record's reference and `status: "completed"`. This action ends the current job: put required record creation before it. A returned reference confirms the callback request was recorded; it does not mean a teammate has called the customer.

### 3. Expose and authorize the endpoint

Open **Platform → API platform → API collections**, create an **API recipe collection** from that folder and configure the recipe endpoint. Activate the endpoint; new endpoints start inactive. Create an API client and an API key using **Auth Token**, assign only this collection and enable the key. Copy the endpoint URL and token. Requests send the token in the `api-token` header, not the Developer API's bearer header.

### 4. Verify the handoff

The administrator supplies the activated endpoint URL, API token, request schema, a verified test customer/number and the expected record reference. Run one test from the API Platform tester and inspect the matching recipe job and queue entry. Also verify an invalid customer or malformed number is rejected before any queue write.

Provider setup: [API recipe setup](https://docs.workato.com/api-mgmt/api-recipes/walkthrough), [API collection activation](https://docs.workato.com/en/api-mgmt/api-collections/recipe-collection.html) and [client authentication](https://docs.workato.com/en/api-mgmt/calling-apis.html).

### Create the Voiceflow request

#### Studio

### 1. Store the service credential

Open your test project in [Agent studio](https://creator.voiceflow.com), then **More → Secrets**. Create `workato_token` with the credential supplied by the service owner. Creating its default also writes Main's Published value, so keep initial setup in a test project. If the selected Environment has a different Draft credential, set its Draft override too.

### 2. Create a request variable

Open **More → Variables**, create `workato_request` with an empty default and ask your application developer to populate it with the [prepared request](#run-request). For a Studio Run test, temporarily set its default to the developer's prepared test string in this isolated test project; backend runtime variables do not automatically populate Studio Run. Clear the default after that test.

### 3. Configure the API request

Open **Agent → Global tools → + → API** and name the tool **Request a support callback**. Choose **POST**, set the owner-supplied endpoint and add the headers below. Set the raw JSON body to `{payload}`.

| Field | Value |
| --- | --- |
| Name | `Request a support callback` |
| Method | `POST` |
| URL | `https://YOUR_WORKATO_ENDPOINT` |
| Header: api-token | `{authorization}` |
| Header: Content-Type | `application/json` |
| Raw JSON body | `{payload}` |

Native Workato API request editor with configured endpoint, headers and raw request body — Configure the deployed Workato endpoint and its request fields.

### 4. Bind inputs before running

Open the attached tool's inputs. Open `authorization` and set its **Default value** to the Secret `workato_token`, and set `payload`'s **Default value** to `workato_request`. Keep **Async execution** off so the agent receives this call's response. The provider workflow may still return a pending receipt.

#### Developer

Set `VF_TOKEN`, `PROJECT_ID` and `ENVIRONMENT` for the test project. Set `PROVIDER_CREDENTIAL` to the API Platform Auth Token. The service owner supplies `PROVIDER_URL` and the verified test request.

Save this definition as `workato-tool.json`, replacing the illustrative URL with `PROVIDER_URL`. Braced names declare inputs on this API tool; they are bound to Secrets/variables on its attachment later.

```json
{
  "name": "Request a support callback",
  "description": "Run the approved Workato request for the customer verified by the application.",
  "httpMethod": "post",
  "url": "https://YOUR_WORKATO_ENDPOINT",
  "headers": [
    {
      "key": "api-token",
      "value": "{authorization}"
    },
    {
      "key": "Content-Type",
      "value": "application/json"
    }
  ],
  "body": {
    "type": "raw-input",
    "contentType": "json",
    "content": "{payload}"
  }
}
```

#### API

```sh
jq -n --arg value "$PROVIDER_CREDENTIAL" \
  '{name:"workato_token",visibility:"restricted",defaultValue:$value}' |
curl --fail-with-body --silent --show-error \
  "https://realtime-api.voiceflow.com/v2/stable/secret?projectID=$PROJECT_ID" \
  -H "Authorization: Bearer $VF_TOKEN" -H 'Content-Type: application/json' --data-binary @-

curl --fail-with-body --silent --show-error \
  "https://realtime-api.voiceflow.com/v2/stable/variable?projectID=$PROJECT_ID&environmentAlias=$ENVIRONMENT" \
  -H "Authorization: Bearer $VF_TOKEN" -H 'Content-Type: application/json' \
  -d '{"name":"workato_request","color":"#515A63","defaultValue":""}'

curl --fail-with-body --silent --show-error \
  "https://realtime-api.voiceflow.com/v2/stable/api-tool?projectID=$PROJECT_ID&environmentAlias=$ENVIRONMENT" \
  -H "Authorization: Bearer $VF_TOKEN" -H 'Content-Type: application/json' \
  --data-binary @workato-tool.json
```

Save `apiTool.id` as `API_TOOL_ID`, then discover input IDs:

```sh
curl --fail-with-body --silent --show-error \
  "https://realtime-api.voiceflow.com/v2/stable/api-tool-variable?projectID=$PROJECT_ID&environmentAlias=$ENVIRONMENT&apiToolID=$API_TOOL_ID" \
  -H "Authorization: Bearer $VF_TOKEN"

curl --fail-with-body --silent --show-error \
  "https://realtime-api.voiceflow.com/v1/stable/api-tool/$API_TOOL_ID/schema?projectID=$PROJECT_ID&environmentAlias=$ENVIRONMENT" \
  -H "Authorization: Bearer $VF_TOKEN"
```

#### CLI

```sh
jq -n --arg value "$PROVIDER_CREDENTIAL" \
  '{name:"workato_token",visibility:"restricted",defaultValue:$value}' |
vf secret create --project-id "$PROJECT_ID" --output-format json

vf variable create --project-id "$PROJECT_ID" --environment-alias "$ENVIRONMENT" \
  --name workato_request --color-param '#515A63' --default-value '""' --output-format json

vf api-tool create --project-id "$PROJECT_ID" --environment-alias "$ENVIRONMENT" \
  --output-format json < workato-tool.json
```

Save `apiTool.id` as `API_TOOL_ID`, then discover input IDs:

```sh
vf api-tool variable list --project-id "$PROJECT_ID" --environment-alias "$ENVIRONMENT" \
  --api-tool-id "$API_TOOL_ID" --output-format json

vf api-tool get-schema --project-id "$PROJECT_ID" --environment-alias "$ENVIRONMENT" \
  --tool-id "$API_TOOL_ID" --output-format json
```

Creating the Secret default also writes Main's Published value. If your selected Environment uses a different credential, set its [Draft override](/docs/documentation/build/data/secrets#publishing-reverting-and-discarding-changes) before testing. Match each `variables[].name` to its `id` for the attachment; resolve `unresolvedReferences` before continuing.

<a id="run-request"></a>

## Request a support callback

Provide a verified request and use the result from the current call.

Invoke **Request a support callback** when the customer asks for a support callback and confirms its number and reason. The authenticated application supplies the verified identity and prepared request variable before the call; keep those inputs bound to trusted defaults. A returned saved callback reference confirms that the callback request was recorded. It does not confirm that the call happened. For a pending result, explain that work is waiting. For a current failure or missing required fields, say the result could not be confirmed; never reuse an earlier result or automatically repeat an uncertain write.

### Prepare the request

#### Developer

The application developer builds the request from an authenticated customer/resource and the confirmed task. Save this illustrative body as `workato-request.json`, replacing test identities with values the application has verified:

```json
{
  "request_id": "req-test-001",
  "customer_id": "verified-customer-123",
  "reason": "Please call about a delayed delivery.",
  "callback_number": "+14165550148"
}
```

Serialize it with the [literal-safe request encoder](/docs/examples/automation/encode-request.mjs): `node encode-request.mjs workato-request.json > workato-payload.txt`. It preserves quotes, newlines and literal text such as `{customer_name}` without treating that text as a Voiceflow variable or Secret. Do not concatenate customer text into quoted JSON placeholders.

#### Studio

Have your developer deliver the encoded string and populate `workato_request` in the authenticated client's next action **before** this tool runs. They send `variables` on the [runtime action](/docs/api-reference/v4interact/interact-non-stream#streaming-action); creating the variable or session alone does not fill it. For Studio Run, use the temporary test default described above, then clear it. The provider service must enforce customer access and validate the request; tool descriptions do not enforce either.

#### Developer

Read the confirmed body, encode it, and build standalone inputs. This tests the saved request against the selected Environment's Draft; it does not attach the tool or publish the agent.

```sh
node encode-request.mjs workato-request.json > workato-payload.txt
jq -n --rawfile payload workato-payload.txt \
  '{inputs:{authorization:"{workato_token}",payload:$payload}}' > workato-inputs.json
```

#### API

```sh
curl --fail-with-body --silent --show-error \
  "https://realtime-api.voiceflow.com/v1/stable/api-tool/$API_TOOL_ID/execute?projectID=$PROJECT_ID&environmentAlias=$ENVIRONMENT" \
  -H "Authorization: Bearer $VF_TOKEN" -H 'Content-Type: application/json' \
  --data-binary @workato-inputs.json
```

#### CLI

```sh
vf api-tool execute --project-id "$PROJECT_ID" --environment-alias "$ENVIRONMENT" \
  --tool-id "$API_TOOL_ID" --output-format json < workato-inputs.json
```

Require `success: true`, inspect `output.status` and `output.body`, and check the business fields against the service owner's response schema. `truncated: true` means the returned body is incomplete. On timeout or error, inspect provider execution before retrying a write.

### Let the agent use the request

#### Studio

### 1. Describe the trigger and result use

Open the attached **Request a support callback** tool and set **Trigger** to the condition below. Its input defaults must already point to the Secret and prepared request variable; the model must not collect credentials or choose another customer's identifier.

```markdown
Use Request a support callback when the customer asks for this service and the application has supplied the verified request. Confirm the callback number and reason before submission.
Read the current tool result. A completed request record means the callback is recorded, not that the call happened.
If the response is pending, say the request is pending. If the call fails or the required fields are missing, explain that the result could not be confirmed. Never reuse an earlier result or automatically repeat a write.
```

Native attached Workato tool with a trusted payload default and invocation trigger — Bind the prepared request input before testing the callback conversation.

### 2. Test the conversation

In **Run**, use the verified test request. Ask "Please arrange a callback about my delayed delivery." and confirm the intended tool runs with the fixed identity and prepared payload. Inspect the current tool result in Run and compare it with the recorded callback request. Also test the rejected-resource case: the agent must not claim success or expose another customer's data.

#### Developer

Save this as `workato-attachment.json`. Replace `YOUR_API_TOOL_ID` and each input ID with the values discovered above. The payload and credential are defaults, not model-collected inputs.

```json
{
  "type": "api",
  "apiToolID": "YOUR_API_TOOL_ID",
  "target": {
    "global": true
  },
  "description": "Use when the customer requests a callback and confirms its number and reason, after the application supplies the prepared request. A saved reference confirms the callback was recorded, not that the call happened. Use only the current result; explain pending or failure and never repeat an uncertain write.",
  "asyncExecution": false,
  "inputVariables": {
    "authorization": {
      "apiToolInputVariableID": "AUTHORIZATION_INPUT_ID",
      "required": false,
      "defaultValue": "{workato_token}"
    },
    "payload": {
      "apiToolInputVariableID": "PAYLOAD_INPUT_ID",
      "required": false,
      "defaultValue": "{workato_request}"
    }
  }
}
```

#### API

```sh
curl --fail-with-body --silent --show-error \
  "https://realtime-api.voiceflow.com/v2/stable/tool?projectID=$PROJECT_ID&environmentAlias=$ENVIRONMENT" \
  -H "Authorization: Bearer $VF_TOKEN" -H 'Content-Type: application/json' \
  --data-binary @workato-attachment.json
```

#### CLI

```sh
vf tool create --project-id "$PROJECT_ID" --environment-alias "$ENVIRONMENT" \
  --output-format json < workato-attachment.json
```

Your authenticated backend supplies the encoded payload as `variables.workato_request` on the next [runtime action](/docs/api-reference/v4interact/interact-non-stream#streaming-action). Use a test client bound to this project's Draft, ask for a callback and inspect the emitted tool call, current response and agent answer. Verify both the successful and rejected-resource cases. The backend/provider enforces access; the description is model guidance, not an authorization gate.

The attached API tool returns the provider body to the agent. For a Workflow's **Capture response**, paths start at that body: for example `request_id` rather than standalone `output.body.request_id`. A missing capture can leave an earlier variable value unchanged; clear result variables before a Workflow call and branch on the current HTTP/business outcome. These Global tool examples use the current result directly.

<a id="maintaining-the-connection"></a>

## Maintaining the connection

Inspect provider execution, update credentials and test the intended deployment.

| Symptom | Check |
| --- | --- |
| Endpoint unavailable | Check collection endpoint activation and that the API recipe is running. |
| 401/403 | Check the API client/key is enabled and assigned this collection; use `api-token` for Auth Token authentication. |
| Recipe fails after creating work | Inspect the job and callback queue by `request_id` before retrying. A response error does not roll back earlier steps. |
| HTTP 200 with an error body | Read the recipe's business result; HTTP success alone does not prove the queue write. |
| Timeout | Look up the original recipe job and request before replaying; keep the same deduplication key for the same confirmed request. |

### Replace a credential

### 1. Inspect the original provider execution

Use the request ID and execution time to find the provider run and its downstream record. A timeout can follow a completed side effect; reconcile that state before repeating a write.

### 2. Update the intended credential version

#### Studio

Open the same project and **More → Secrets**, select the provider Secret and update the target Environment's **Draft value** for testing. After validation, explicitly set the Published value for the intended Environment; this changes the credential serving live traffic.

#### Developer

Retain `secret.id` from creation as `SECRET_ID`, set `PROVIDER_CREDENTIAL` to the replacement and use the value operation below. After validation, explicitly set the Published value for the intended Environment; this changes the credential serving live traffic.

#### Developer

Save the Draft update body as `credential-value.json`:

```sh
jq -n --arg value "$PROVIDER_CREDENTIAL" --arg env "$ENVIRONMENT" \
  '{value:$value,environmentAlias:$env,versionVariant:"draft"}' > credential-value.json
```

#### API

```sh
curl --fail-with-body --silent --show-error -X PUT \
  "https://realtime-api.voiceflow.com/v1/stable/secret/$SECRET_ID/value?projectID=$PROJECT_ID" \
  -H "Authorization: Bearer $VF_TOKEN" -H 'Content-Type: application/json' \
  --data-binary @credential-value.json
```

#### CLI

```sh
vf secret set-value --project-id "$PROJECT_ID" --secret-id "$SECRET_ID" \
  --output-format json < credential-value.json
```

For the selected Environment's Published credential, change `versionVariant` to `published` after the Draft test. To replace the project default, omit `environmentAlias` and `versionVariant`; this also writes Main's Published value. Test the intended connection before changing a live default.

Before launch, select the target Environment and supply the provider Secret's **Default value** for its published agent; a Draft override alone does not supply Published. [Publish the tested configuration](/docs/documentation/deploy/environments/publishing), then repeat the conversation test against that Environment's published client and verify the provider account/resource it reaches.

Rotate the credential with the provider owner, update the relevant Secret default/Environment overrides, and retest the existing tool. Removing a tool from Voiceflow does not remove the provider deployment or revoke its credential. Disable/revoke access in Workato when retiring the integration, then remove the unused attachment and API resource.
