> For the complete documentation index, see [llms.txt](https://docs.planetcrust.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.planetcrust.com/human-connections/google/gmail/action-create-draft.md).

# Action: Create Draft

<p align="center"><a class="button primary" data-icon="circle-caret-right">Try @Human</a><a class="button primary" data-icon="check">Buy @Human Subscriptions</a><a class="button primary" data-icon="comments">Join @Human Community</a></p>

<figure><img src="/files/5kJqaCa4hNci9Yb597Jb" alt="" width="188"><figcaption></figcaption></figure>

<p align="center">The Create Draft action starts a new unsent email in Gmail with optional pre-filled content.</p>

{% embed url="<https://www.youtube.com/watch?v=CyuUuaBSZzA>" %}

#### Example User Story

I want to create a draft for next week's newsletter so I can refine the content before sending.

#### Fields

| Field Name | Field Type | Required |
| ---------- | ---------- | -------- |
| to         | String     | Yes      |
| subject    | String     | No       |
| body       | String     | No       |
| draftId    | String     | No       |
| messageId  | String     | No       |

### Related Connections

[Gmail](/human-connections/google/gmail.md)

### Related Automations

```
{
  "handle": "create-draft",
  "state": "inDev",
  "meta": {
    "short": "Create Draft",
    "description": "Creates a new draft email in Gmail."
  },
  "input": [
    {
      "name": "to",
      "type": "String",
      "required": true,
      "meta": {
        "description": "Recipient email address"
      }
    },
    {
      "name": "subject",
      "type": "String",
      "required": false,
      "meta": {
        "description": "Subject of the email"
      }
    },
    {
      "name": "body",
      "type": "String",
      "required": false,
      "meta": {
        "description": "Body content of the email"
      }
    }
  ],
  "output": [
    {
      "name": "draftId",
      "type": "String",
      "selector": ["id"],
      "meta": {
        "description": "ID of the created draft"
      }
    },
    {
      "name": "messageId",
      "type": "String",
      "selector": ["message", "id"],
      "meta": {
        "description": "ID of the message in the draft"
      }
    }
  ],
  "steps": [
    {
      "type": "http",
      "http": {
        "method": "POST",
        "path": "/gmail/v1/users/me/drafts",
        "headers": {
          "Content-Type": "application/json"
        },
        "bodyTemplate": {
          "value": "{\"message\": {\"raw\": \"{{base64EncodedEmail}}\"}}",
          "placeholders": [
            {
              "name": "accessToken",
              "type": "String",
              "description": "OAuth access token for Gmail API",
              "required": true
            },
            {
              "name": "base64EncodedEmail",
              "type": "String",
              "description": "Base64 URL-safe encoded email message",
              "required": true
            }
          ]
        }
      }
    }
  ]
}

```

### Code (Apache v2.0): Operation

<p align="center"><a class="button primary" data-icon="square-caret-right">Try @Human</a><a class="button primary" data-icon="check">Buy @Human Subscription</a><a class="button primary" data-icon="comments">Join @Human Community</a></p>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.planetcrust.com/human-connections/google/gmail/action-create-draft.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.