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

# Batch Tasks

> Submit N tasks in parallel, track all to completion, and return a results map.

<Note>
  This skill is available as a machine-readable YAML playbook — append `.md` to any docs page for raw markdown, or install the [Framelane skill](https://framelane.io/skill.md). Drive the calls through the authenticated action MCP at `https://mcp.framelane.io/mcp`.
  Load it into any MCP-capable agent to get the complete workflow without writing integration code.
</Note>

## What this skill does

Submits an array of task requests in parallel to `POST /v1/tasks/{type}`, polls all task IDs concurrently until every job reaches a terminal status, and returns a results map keyed by input index.

## Load via MCP

```
@framelane-skill:batch-tasks
```

## Inputs

| Name    | Required     | Description                                                                                                                                          |
| ------- | ------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
| `tasks` | **required** | Array of `{type, body}` objects. `type` is a task slug (e.g. `transcribe`, `remove-background`); `body` is the full request body for that task type. |

## Output

Returns `results` — a map from task index to `{task_id, status, artifact_url, error}`.