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

# Get Style Agent Workflow

GET https://api.markup.ai/style-agent/workflows/{workflow_id}

Get the status and result of a Style Agent content-check run.

Poll with the workflow id returned by ``POST /style-agent/run``. While the
run is in progress the status reflects its state; once it completes the
response includes the result.

Reference: https://docs.markup.ai/developer-reference/api-reference/style-agent/get-style-agent-workflow

## Authentication

- `Authorization` header (bearer token, required) — Bearer authentication of the form `Bearer <token>`, where token is your auth token.

## Request

### Path parameters

- `workflow_id` (string, required)

## Response

### 200

Successful Response

- `workflow_id` (string, required) — Workflow ID
- `status` (enum, required) — Current status
  - Allowed values: `running`, `completed`, `failed`, `timed_out`, `cancelled`
- `started_at` (datetime, required) — Start time
- `agent_id` (string, optional, default: ) — Agent that ran this workflow
- `document_ref` (string, optional, nullable) — Caller-provided document identifier.
- `check_type` (enum, optional) — How this check is counted: 'batch' for a document checked as part of a batch, 'interactive' for a direct /run check.
  - Allowed values: `interactive`, `automated`, `batch`, `baseline`
- `assigned` (boolean, optional, default: true) — Whether the check counts as authoring activity for an author.
- `batch_id` (string, optional, nullable) — Owning batch id (agbw\_\<nanoid>); null unless this is a batch check.
- `result` (StyleAgentResult, optional, nullable) — Result (if completed)
- `completed_at` (datetime, optional, nullable) — Workflow completion time

## Errors

### 401 Unauthorized Error

Authentication failed or no valid API key provided.

- `detail` (string, required) — A description of the error that occurred.
- `status` (integer, required) — The HTTP status code generated by the server for this issue
- `request_id` (string, required) — A unique ID associated with the HTTP request.

### 403 Forbidden Error

Forbidden

- `detail` (string, required) — A description of the error that occurred.
- `status` (integer, required) — The HTTP status code generated by the server for this issue
- `request_id` (string, required) — A unique ID associated with the HTTP request.

### 404 Not Found Error

Workflow not found

- `detail` (string, required) — A description of the error that occurred.
- `status` (integer, required) — The HTTP status code generated by the server for this issue
- `request_id` (string, required) — A unique ID associated with the HTTP request.

### 422 Unprocessable Entity Error

Validation Error

- `detail` (list of ValidationError, optional)

### 500 Internal Server Error

Failed to retrieve workflow status

- `detail` (string, required) — A description of the error that occurred.
- `status` (integer, required) — The HTTP status code generated by the server for this issue
- `request_id` (string, required) — A unique ID associated with the HTTP request.

## Types

### StyleAgentResult

Result of a Style Agent content check. Only the ``analysis`` block is typed here — issues, quality scores, and any agent-specific keys flow through unchanged (``extra="allow"``). Validating ``analysis`` at this edge also mirrors the legacy ``targetId`` naming onto the canonical ``styleGuideId`` keys for results persisted before the rename.

- `analysis` (StyleAgentAnalysis, optional, nullable) — Style guide, content profile, and readability metadata for the checked document. Omitted while the run is in progress and for organizations without numeric scoring.

### ValidationError

- `loc` (list of ValidationErrorLocItems, required)
- `msg` (string, required)
- `type` (string, required)
- `input` (any, optional)
- `ctx` (ValidationErrorCtx, optional)

### StyleAgentAnalysis

Style guide, content profile, and readability metadata forwarded from SLS. Cortex populates this from the language-service ``data.analysis`` block (legacy ``targetId`` naming) and helios_one republishes it on the style-agent API surface. ``styleGuideId`` / ``styleGuideDisplayName`` are the canonical public keys; the legacy ``targetId`` / ``targetDisplayName`` keys carry the same values (and are marked deprecated in the schema) until removed in a future API version. The mirror runs on validation, so results persisted before the rename gain the canonical keys when re-validated.

- `styleGuideId` (string, optional, nullable)
- `styleGuideDisplayName` (string, optional, nullable)
- `contentProfileId` (string, optional, nullable)
- `contentProfileDisplayName` (string, optional, nullable)
- `words` (integer, optional, nullable)
- `sentences` (integer, optional, nullable)
- `clarityIndex` (double, optional, nullable)
- `informalityIndex` (double, optional, nullable)
- `livelinessIndex` (double, optional, nullable)
- `fleschReadingEase` (double, optional, nullable)
- `fleschKincaid` (double, optional, nullable) — Flesch-Kincaid grade level: the approximate US school grade needed to read the text. Lower is easier to read. It has no fixed range.
- `targetId` (string, optional, nullable, deprecated)
- `targetDisplayName` (string, optional, nullable, deprecated)

### ValidationErrorLocItems

- string
- integer

### ValidationErrorCtx

## Examples

**Response**

```json
{
  "workflow_id": "string",
  "status": "running",
  "started_at": "2024-01-15T09:30:00Z",
  "agent_id": "",
  "document_ref": "string",
  "check_type": "interactive",
  "assigned": true,
  "batch_id": "string",
  "result": {
    "analysis": {
      "styleGuideId": "string",
      "styleGuideDisplayName": "string",
      "contentProfileId": "string",
      "contentProfileDisplayName": "string",
      "words": 1,
      "sentences": 1,
      "clarityIndex": 1.1,
      "informalityIndex": 1.1,
      "livelinessIndex": 1.1,
      "fleschReadingEase": 1.1,
      "fleschKincaid": 1.1,
      "targetId": "string",
      "targetDisplayName": "string"
    }
  },
  "completed_at": "2024-01-15T09:30:00Z"
}
```

**SDK Code**

```python
import requests

url = "https://api.markup.ai/style-agent/workflows/workflow_id"

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

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

print(response.json())
```

```javascript
const url = 'https://api.markup.ai/style-agent/workflows/workflow_id';
const options = {method: 'GET', 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
package main

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

func main() {

	url := "https://api.markup.ai/style-agent/workflows/workflow_id"

	req, _ := http.NewRequest("GET", 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
require 'uri'
require 'net/http'

url = URI("https://api.markup.ai/style-agent/workflows/workflow_id")

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

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

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

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.get("https://api.markup.ai/style-agent/workflows/workflow_id")
  .header("Authorization", "Bearer <token>")
  .asString();
```

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

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://api.markup.ai/style-agent/workflows/workflow_id', [
  'headers' => [
    'Authorization' => 'Bearer <token>',
  ],
]);

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

```csharp
using RestSharp;

var client = new RestClient("https://api.markup.ai/style-agent/workflows/workflow_id");
var request = new RestRequest(Method.GET);
request.AddHeader("Authorization", "Bearer <token>");
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

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

let request = NSMutableURLRequest(url: NSURL(string: "https://api.markup.ai/style-agent/workflows/workflow_id")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"
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()
```